blueswarm image.png
Swarm robotics involves scores of individual mobile robots that mimic the collective behavior demonstrated by animals. Certain robots, like the Bluebot pictured here, perform some of the same behaviors as a school of fish, such as aggregation, dispersion, and searching.
Courtesy of Radhika Nagpal, Harvard University

Schooling robots to behave like fish

Radhika Nagpal has created robots that can build towers without anyone in charge. Now she’s turned her focus to fulfillment center robots.

When Radhika Nagpal was starting graduate school in 1994, she and her future husband went snorkeling in the Caribbean. Nagpal, who grew up in a landlocked region of India, had never swum in the ocean before. It blew her away.

“The reef was super healthy and colorful, like being in a National Geographic television show,” she recalled. “As soon as I put my face in the water, this whole swarm of fish came towards me and then swerved to the right.”

Meet the Blueswarm
Blueswarm comprises seven identical miniature Bluebots that combine autonomous 3D multi-fin locomotion with 3D camera-based visual perception.

The fish fascinated her. As she watched, large schools of fish would suddenly stop or switch direction as if they were guided by a single mind. A series of questions occurred to her. How did they communicate with one another? What rules — think of them as algorithms — produced such complex group behaviors? What environmental prompts triggered their actions? And most importantly, what made collectives so much smarter and more successful than their individual members?

Radhika Nagpal is a professor of computer science at Harvard University’s Wyss Institute for Biologically Inspired Engineering and an Amazon Scholar
Radhika Nagpal is a professor of computer science at Harvard University’s Wyss Institute for Biologically Inspired Engineering and an Amazon Scholar.

Since then, Nagpal, a professor of computer science at Harvard University’s Wyss Institute for Biologically Inspired Engineering and an Amazon Scholar, has gone on to build swarming robots. Swarm robotics involves scores of individual mobile robots that mimic the collective behavior demonstrated by animals, e.g. how flocks of birds or schools of fish move together to achieve some end. The robots act as if they, too, were guided by a single mind, or, more precisely, a single computer. Yet they are not.

Instead, they follow a relatively simple set of behavioral rules. Without any external orders or directions, Nagpal’s swarms organize themselves to carry out surprisingly complex tasks, like spontaneously synchronizing their behavior, creating patterns, and even building a tower.

More recently, her lab developed swimming robots that performed some of the same behaviors as a school of fish, such as aggregation, dispersion, and searching. All without a leader.

Nagpal’s work demonstrates both how far we have come in creating self-organizing robot swarms that can perform tasks — and how far we still must go to emulate the complex tapestries woven by nature. It is a gap that Nagpal hopes to close by uncovering the secrets of swarm intelligence to make swarm robots far more useful.

Amorphous computing

The Caribbean fish sparked Nagpal’s imagination because she was already interested in distributed computing, where multiple computers collaborate to solve problems or transfer information without any single computer running the show. At MIT, where she had begun her PhD program, she was drawn to an offshoot of the field called amorphous computing. It investigates how limited, unreliable individuals — from cells to ants to fish — organize themselves to perform often complex tasks consistently without any hierarchies.

Amorphous computing was “hardware agnostic.” This meant that it sought rules that guided this behavior in both living organisms and computer systems. It asked, for example, how identical cells in an embryo form all the organs of an animal, how ants find the most direct route to food, or how fish coordinate their movements. By studying nature, these computer scientists hoped to build computer networks that operated on the same principles.

I got excited about how nature makes these complicated, distributed, mobile networks. Those multi-robot systems became a new direction of my research
Radhika Nagpal

After completing her doctoral work on self-folding materials inspired by how cells form tissues, Nagpal began teaching at Harvard. While there, she was visited by her friend James McLurkin, a pioneer in swarm robotics at MIT and iRobot.

“James is the one that got me into robot swarms by introducing me to all the things that ant and termite colonies do,” Nagpal said. “I got excited about how nature makes these complicated, distributed, mobile networks. James was developing that used similar principles to move around and work together. Those multi-robot systems became a new direction of my research.”

She was particularly taken by Namibian termites, which build large-scale nest mounds with multiple chambers and complex ventilation systems, often as high as 8 feet tall.

“As far as we know, there isn’t a blueprint or an a priori distribution between who’s doing the building and who is not. We know the queen does not set the agenda,” she explained. “These colonies start with hundreds of termites and expand their structure as they grow.”

The question fascinated her. “I have no idea how that works,” she said. “I mean, how do you create systems that are so adaptive?”

Finding the rules

Researchers have spent decades answering that question. One way, they found, is to act locally. Take, for example, a flock of geese at a pond. If one or two birds on the outside of the flock see a predator, they grow agitated and fly off, alerting the next nearest birds. The message percolates through flock. Once a certain number of birds have “voted” to fly off, the rest follow without any hesitation. They are not following a leader, only reacting only to the birds next to them.

How dynamic circle formation works

The same type of local behaviors could be used to make driverless vehicles safer. An autonomous vehicle, Nagpal explains, does not have to reason about all the other cars on the road, only the ones around it. By focusing on nearby vehicles, these distributed systems use less processing power without losing the ability to react to changes very quickly.

Such systems are highly scalable. “Instead of having to reason about everybody, your car only has to reason about its five neighbors,” Nagpal said. “I can make the system very large, but each individual’s reasoning space remains constant. That’s a traditional notion of scalable —the amount of processing per vehicle stays constant, but we’re allowed to increase the size of the system.”

Another key to swarm behavior involves embodied intelligence, the idea that brains interact with the world through bodies that can see, hear, touch, smell, and taste. This is a type of intelligence, too, Nagpal argues.

It’s almost like each individual fish acts like a distributed sensor. Instead of me doing all the work, somebody on the left can say, ‘Hey, I saw something.’ When the group divides the labor so that some of us look out for predators while the rest of us eat, it costs less in terms of energy and resources.
Radhika Nagpal

“When you think of an ant, there is not a concentrated set of neurons there,” she said, referring to the ant’s 20-microgram brain. “Instead, there is a huge amount of awareness in the body itself. I may wonder how an ant solves a problem, but I have to realize that somehow having a physical body full of sensors makes that easier. We do not really understand how to think about that still.”

Local actions, scalable behavior, and embodied intelligence are among the factors that make swarms successful. In fact, researchers have shown that the larger a school of fish, the more successful it is at evading predators, finding food, and not getting lost.

“It’s almost like each individual fish acts like a distributed sensor,” Nagpal said. “Instead of me doing all the work, somebody on the left can say, ‘Hey, I saw something.’ When the group divides the labor so that some of us look out for predators while the rest of us eat, it costs less in terms of energy and resources than trying to eat and look out for predators all by yourself.

“What’s really interesting about large insect colonies and fish schools is that they do really complicated things in a decentralized way, whereas people have a tendency to build hierarchies as soon as we have to work together,” she continued. “There is a cost to that, and if we try to do that with that with robots, we replicate the whole management structure and cost of a hierarchy.”

So Nagpal set out to build robots swarms that worked without top-down organization.

Animal behavior

A typical process in Nagpal’s group starts by identifying an interesting natural behavior and trying to discover the rules that generate those actions. Sometimes, they are surprisingly simple.

Take, for example, some behaviors exhibited by Nagpal’s colony of 1,000 interactive robots, each the size of quarter and each communicating with its nearest neighbors wirelessly. The robots will self-assemble into a simple line with a repeating color pattern based on only two rules: a motion rule that allows them to move around any stationary robots, and a pattern rule that tells them to take on the color of their two nearest neighbors.

Other combinations of simple rules spontaneously synchronize the blinking of robot lights, guide migrations, and get the robots to form the letter “K.”

Most impressively, Nagpal and her lab used a behavior found in termites, called stigmergy, to prompt self-organized robot swarms to build a tower. Stigmergy involves leaving a mark on the environment that triggers a specific behavior by another member of the group.

Stigmergy plays a role in how termites build their huge nests. One termite may sense that a spot would make a good place to build, so it puts down its equivalent of a mud brick. When a second termite comes along, the brick triggers it to place its brick there. As the number of bricks increase, the trigger grows stronger and other termites begin building pillars nearby. When they grow high enough, something triggers the termites to begin connecting them with roofs.

“The building environment has become a physical memory of what should happen next,” Nagpal said.

Nagpal used that type of structural memory to prompt her robotic swarm to build a ziggurat tower. The instructions included a motion rule about how to move through the tower and a pattern rule about where to place the blocks. She then built some small, block-carrying robots that built a smaller but no less impressive structure.

Her lab developed a compiler that could generate algorithms that would enable the robots to build specific types of structures — perhaps towers with minarets — by interacting with stigmergic physical memories. One day, algorithm-driven robots could move sandbags to shore up a levee in a hurricane or buttress a collapsed building. They could even monitor coral reefs, underwater infrastructure, and pipelines — if they could swim.

Schooling robofish

From the start, Nagpal wanted to build her own school of robotic fish, but the hardware was simply too clunky to make them practical. That changed with the advent of smartphones, with their low-cost, low-power processors, sensors, and batteries.

In 2018, she got her chance when she received an Amazon Machine Learning Research Award. This allowed her to build Blueswarm, a group of robotic fish that performed tasks like those she observed in the Caribbean years ago.

Each Bluebot is just four inches long, but it packs a small Raspberry Pi computer, two fish-eye cameras, and three blue LED lights. It also has a tail (caudal) fin for thrust, a dorsal fin to move up or down, and side fins (pectoral fins) to turn, stop, or swim backward.

Bluebots do not use Wi-Fi, GPS, or external cameras to communicate their positions without error. Instead, she wants to explore what behaviors are possible relying only on cameras and local perception of one’s mates.

How multi-behavior search works

Researchers, she explained, find it difficult to rely only upon local perception. It has been difficult to tackle fundamental questions, like how does a robot visually detect other members of the swarm, how they parse information, and what happens when one member moves in front of another. Limiting Bluebot sensing to local perception forces Nagpal and her team to think more deeply about what robots really need to know about their neighbors, especially when data is limited and imprecise. 

Bluebots can mimic several fish school behaviors by tracking LED lights on the neighboring fishbots around them. Using 3D cameras and simple algorithms, they estimate distance between lights on neighboring fish. (The closer they appear, the further the fish.)

Nagpal’s seven Bluebots form a circle (called milling) by turning right if there is a robot in front of them. If there is no robot, they turn left. After a few moments, the school will be swimming in a circle, a formation fish use to trap prey.

They can also search for a target flashing red light. First, the school disperses within the tank. When a Bluebot finds the red LED, it begins to flash its lights. This signals the nearest Bluebots to aggregate, followed by the rest. If a single robot had to conduct a similar search by itself, it would take significantly longer.

These behaviors are impressive for robots, but represent a small subset of fish school behaviors. They also take place in a static fish tank populated by only one school of robot fish. To go further, Nagpal wants to improve their sensors and perhaps use machine learning to discover new rules that could be combined to produce the aquatic equivalent of a tower.

In the end, though, Nagpal does not want to build a better fish. Instead, she wants to apply the lessons she has learned to real-world robots. She is doing just that during a sabbatical working at Amazon, which operates the largest fleet of robots — more than 200,000 units — in the world.

Practical uses

Nagpal had little previous experience working in industry, but she jumped at the chance to work with Amazon.

“There are few others with hundreds of robots moving around safely in a facility space,” she said. “And the opportunity to work on algorithms in a deployed system was very exciting."

There are few others [like Amazon] with hundreds of robots moving around safely in a facility space. And the opportunity to work on algorithms in a deployed system was very exciting.
Radhika Nagpal

“The other factor is that Amazon’s robots do a mix of centralized and decentralized decision-making," she continued. "The robots plan their own paths, but they also use the cloud to know more. That lets us ask: Is it better to know everything about all your neighbors all the time? Or is it better to only know about the neighbors that are closer to you?”

Her current focus is on sortation centers, where robots help route packages to shipping stations sorted by ZIP codes. Not surprisingly, robots setting out from multiple points to dozens of different locations require a degree of coordination. Amazon’s robots are already aware of other robots. If they see one, they will choose an alternate route. But what path should they take, Nagpal asks. She wants to make sure those robots are making the most effective possible choices.

Cities already manage this. They limit access to some roads, change speed limits, and add one-way streets. Computer networks do it as well, rerouting traffic when packet delivery slows down.

Some of those concepts, such as one-way travel lanes, also work in sortation centers. They could act as stigmergic signals to guide robot behavior. She also believes there might be a way to create simple swarm behaviors that enable robots to react to advanced data about incoming packages.

Once her sabbatical is over, Nagpal plans to return to the lab. She wants to keep working on her Bluebots, improving their vision, and turning them loose in environments that look more like the coral reef she went snorkeling in 25 years ago.

She is also dreaming of swarms of bigger robots for use in construction or trash collection.

“Maybe we could do what Amazon is doing, but do it outside,” she said. “We could have swarms of robots that actually do some sort of practical task. At Amazon, that task is delivery. But given Boston’s snowstorms, I think shoveling the sidewalks would be nice.”

Research areas

Related content

GB, MLN, Edinburgh
We’re looking for a Machine Learning Scientist in the Personalization team for our Edinburgh office experienced in generative AI and large models. You will be responsible for developing and disseminating customer-facing personalized recommendation models. This is a hands-on role with global impact working with a team of world-class engineers and scientists across the Edinburgh offices and wider organization. You will lead the design of machine learning models that scale to very large quantities of data, and serve high-scale low-latency recommendations to all customers worldwide. You will embody scientific rigor, designing and executing experiments to demonstrate the technical efficacy and business value of your methods. You will work alongside a science team to delight customers by aiding in recommendations relevancy, and raise the profile of Amazon as a global leader in machine learning and personalization. Successful candidates will have strong technical ability, focus on customers by applying a customer-first approach, excellent teamwork and communication skills, and a motivation to achieve results in a fast-paced environment. Our position offers exceptional opportunities for every candidate to grow their technical and non-technical skills. If you are selected, you have the opportunity to make a difference to our business by designing and building state of the art machine learning systems on big data, leveraging Amazon’s vast computing resources (AWS), working on exciting and challenging projects, and delivering meaningful results to customers world-wide. Key job responsibilities Develop machine learning algorithms for high-scale recommendations problems. Rapidly design, prototype and test many possible hypotheses in a high-ambiguity environment, making use of both quantitative analysis and business judgement. Collaborate with software engineers to integrate successful experimental results into large-scale, highly complex Amazon production systems capable of handling 100,000s of transactions per second at low latency. Report results in a manner which is both statistically rigorous and compellingly relevant, exemplifying good scientific practice in a business environment.
IN, TS, Hyderabad
Welcome to the Worldwide Returns & ReCommerce team (WWR&R) at Amazon.com. WWR&R is an agile, innovative organization dedicated to ‘making zero happen’ to benefit our customers, our company, and the environment. Our goal is to achieve the three zeroes: zero cost of returns, zero waste, and zero defects. We do this by developing products and driving truly innovative operational excellence to help customers keep what they buy, recover returned and damaged product value, keep thousands of tons of waste from landfills, and create the best customer returns experience in the world. We have an eye to the future – we create long-term value at Amazon by focusing not just on the bottom line, but on the planet. We are building the most sustainable re-use channel we can by driving multiple aspects of the Circular Economy for Amazon – Returns & ReCommerce. Amazon WWR&R is comprised of business, product, operational, program, software engineering and data teams that manage the life of a returned or damaged product from a customer to the warehouse and on to its next best use. Our work is broad and deep: we train machine learning models to automate routing and find signals to optimize re-use; we invent new channels to give products a second life; we develop highly respected product support to help customers love what they buy; we pilot smarter product evaluations; we work from the customer backward to find ways to make the return experience remarkably delightful and easy; and we do it all while scrutinizing our business with laser focus. You will help create everything from customer-facing and vendor-facing websites to the internal software and tools behind the reverse-logistics process. You can develop scalable, high-availability solutions to solve complex and broad business problems. We are a group that has fun at work while driving incredible customer, business, and environmental impact. We are backed by a strong leadership group dedicated to operational excellence that empowers a reasonable work-life balance. As an established, experienced team, we offer the scope and support needed for substantial career growth. Amazon is earth’s most customer-centric company and through WWR&R, the earth is our customer too. Come join us and innovate with the Amazon Worldwide Returns & ReCommerce team!
US, WA, Seattle
Prime Video is a first-stop entertainment destination offering customers a vast collection of premium programming in one app available across thousands of devices. Prime members can customize their viewing experience and find their favorite movies, series, documentaries, and live sports – including Amazon MGM Studios-produced series and movies; licensed fan favorites; and programming from Prime Video add-on subscriptions such as Apple TV+, Max, Crunchyroll and MGM+. All customers, regardless of whether they have a Prime membership or not, can rent or buy titles via the Prime Video Store, and can enjoy even more content for free with ads. Are you interested in shaping the future of entertainment? Prime Video's technology teams are creating best-in-class digital video experience. As a Prime Video technologist, you’ll have end-to-end ownership of the product, user experience, design, and technology required to deliver state-of-the-art experiences for our customers. You’ll get to work on projects that are fast-paced, challenging, and varied. You’ll also be able to experiment with new possibilities, take risks, and collaborate with remarkable people. We’ll look for you to bring your diverse perspectives, ideas, and skill-sets to make Prime Video even better for our customers. With global opportunities for talented technologists, you can decide where a career Prime Video Tech takes you! In Prime Video READI, our mission is to automate infrastructure scaling and operational readiness. We are growing a team specialized in time series modeling, forecasting, and release safety. This team will invent and develop algorithms for forecasting multi-dimensional related time series. The team will develop forecasts on key business dimensions with optimization recommendations related to performance and efficiency opportunities across our global software environment. As a founding member of the core team, you will apply your deep coding, modeling and statistical knowledge to concrete problems that have broad cross-organizational, global, and technology impact. Your work will focus on retrieving, cleansing and preparing large scale datasets, training and evaluating models and deploying them to production where we continuously monitor and evaluate. You will work on large engineering efforts that solve significantly complex problems facing global customers. You will be trusted to operate with complete independence and are often assigned to focus on areas where the business and/or architectural strategy has not yet been defined. You must be equally comfortable digging in to business requirements as you are drilling into design with development teams and developing production ready learning models. You consistently bring strong, data-driven business and technical judgment to decisions. You will work with internal and external stakeholders, cross-functional partners, and end-users around the world at all levels. Our team makes a big impact because nothing is more important to us than delivering for our customers, continually earning their trust, and thinking long term. You are empowered to bring new technologies to your solutions. If you crave a sense of ownership, this is the place to be.
US, WA, Seattle
Amazon Advertising operates at the intersection of eCommerce and advertising, and is investing heavily in building a world-class advertising business. We are defining and delivering a collection of self-service performance advertising products that drive discovery and sales. Our products are strategically important to our Retail and Marketplace businesses driving long-term growth. We deliver billions of ad impressions and millions of clicks daily and are breaking fresh ground to create world-class products to improve both shopper and advertiser experience. With a broad mandate to experiment and innovate, we grow at an unprecedented rate with a seemingly endless range of new opportunities. The Ad Response Prediction team in Sponsored Products organization build advanced deep-learning models, large-scale machine-learning pipelines, and real-time serving infra to match shoppers’ intent to relevant ads on all devices, for all contexts and in all marketplaces. Through precise estimation of shoppers’ interaction with ads and their long-term value, we aim to drive optimal ads allocation and pricing, and help to deliver a relevant, engaging and delightful ads experience to Amazon shoppers. As the business and the complexity of various new initiatives we take continues to grow, we are looking for talented Applied Scientists to join the team. Key job responsibilities As a Applied Scientist II, you will: * Conduct hands-on data analysis, build large-scale machine-learning models and pipelines * Work closely with software engineers on detailed requirements, technical designs and implementation of end-to-end solutions in production * Run regular A/B experiments, gather data, perform statistical analysis, and communicate the impact to senior management * Establish scalable, efficient, automated processes for large-scale data analysis, machine-learning model development, model validation and serving * Provide technical leadership, research new machine learning approaches to drive continued scientific innovation * Be a member of the Amazon-wide Machine Learning Community, participating in internal and external MeetUps, Hackathons and Conferences
US, WA, Seattle
Prime Video is a first-stop entertainment destination offering customers a vast collection of premium programming in one app available across thousands of devices. Prime members can customize their viewing experience and find their favorite movies, series, documentaries, and live sports – including Amazon MGM Studios-produced series and movies; licensed fan favorites; and programming from Prime Video add-on subscriptions such as Apple TV+, Max, Crunchyroll and MGM+. All customers, regardless of whether they have a Prime membership or not, can rent or buy titles via the Prime Video Store, and can enjoy even more content for free with ads. Are you interested in shaping the future of entertainment? Prime Video's technology teams are creating best-in-class digital video experience. As a Prime Video team member, you’ll have end-to-end ownership of the product, user experience, design, and technology required to deliver state-of-the-art experiences for our customers. You’ll get to work on projects that are fast-paced, challenging, and varied. You’ll also be able to experiment with new possibilities, take risks, and collaborate with remarkable people. We’ll look for you to bring your diverse perspectives, ideas, and skill-sets to make Prime Video even better for our customers. With global opportunities for talented technologists, you can decide where a career Prime Video Tech takes you! Key job responsibilities As an Applied Scientist in the Content Understanding Team, you will lead the end-to-end research and deployment of video and multi-modal models applied to a variety of downstream applications. More specifically, you will: - Work backwards from customer problems to research and design scientific approaches for solving them - Work closely with other scientists, engineers and product managers to expand the depth of our product insights with data, create a variety of experiments to determine the high impact projects to include in planning roadmaps - Stay up-to-date with advancements and the latest modeling techniques in the field - Publish your research findings in top conferences and journals About the team Our Prime Video Content Understanding team builds holistic media representations (e.g. descriptions of scenes, semantic embeddings) and apply them to new customer experiences supply chain problems. Our technology spans the entire Prime Video catalogue globally, and we enable instant recaps, skip intro timing, ad placement, search, and content moderation.
IN, HR, Gurugram
We're on a journey to build something new a green field project! Come join our team and build new discovery and shopping products that connect customers with their vehicle of choice. We're looking for a talented Senior Applied Scientist to join our team of product managers, designers, and engineers to design, and build innovative automotive-shopping experiences for our customers. This is a great opportunity for an experienced engineer to design and implement the technology for a new Amazon business. We are looking for a Applied Scientist to design, implement and deliver end-to-end solutions. We are seeking passionate, hands-on, experienced and seasoned Senior Applied Scientist who will be deep in code and algorithms; who are technically strong in building scalable computer vision machine learning systems across item understanding, pose estimation, class imbalanced classifiers, identification and segmentation.. You will drive ideas to products using paradigms such as deep learning, semi supervised learning and dynamic learning. As a Senior Applied Scientist, you will also help lead and mentor our team of applied scientists and engineers. You will take on complex customer problems, distill customer requirements, and then deliver solutions that either leverage existing academic and industrial research or utilize your own out-of-the-box but pragmatic thinking. In addition to coming up with novel solutions and prototypes, you will directly contribute to implementation while you lead. A successful candidate has excellent technical depth, scientific vision, project management skills, great communication skills, and a drive to achieve results in a unified team environment. You should enjoy the process of solving real-world problems that, quite frankly, haven’t been solved at scale anywhere before. Along the way, we guarantee you’ll get opportunities to be a bold disruptor, prolific innovator, and a reputed problem solver—someone who truly enables AI and robotics to significantly impact the lives of millions of consumers. Key job responsibilities Architect, design, and implement Machine Learning models for vision systems on robotic platforms Optimize, deploy, and support at scale ML models on the edge. Influence the team's strategy and contribute to long-term vision and roadmap. Work with stakeholders across , science, and operations teams to iterate on design and implementation. Maintain high standards by participating in reviews, designing for fault tolerance and operational excellence, and creating mechanisms for continuous improvement. Prototype and test concepts or features, both through simulation and emulators and with live robotic equipment Work directly with customers and partners to test prototypes and incorporate feedback Mentor other engineer team members. A day in the life - 6+ years of building machine learning models for retail application experience - PhD, or Master's degree and 6+ years of applied research experience - Experience programming in Java, C++, Python or related language - Experience with neural deep learning methods and machine learning - Demonstrated expertise in computer vision and machine learning techniques.
US, WA, Seattle
Prime Video is a first-stop entertainment destination offering customers a vast collection of premium programming in one app available across thousands of devices. Prime members can customize their viewing experience and find their favorite movies, series, documentaries, and live sports – including Amazon MGM Studios-produced series and movies; licensed fan favorites; and programming from Prime Video add-on subscriptions such as Apple TV+, Max, Crunchyroll and MGM+. All customers, regardless of whether they have a Prime membership or not, can rent or buy titles via the Prime Video Store, and can enjoy even more content for free with ads. Are you interested in shaping the future of entertainment? Prime Video's technology teams are creating best-in-class digital video experience. As a Prime Video team member, you’ll have end-to-end ownership of the product, user experience, design, and technology required to deliver state-of-the-art experiences for our customers. You’ll get to work on projects that are fast-paced, challenging, and varied. You’ll also be able to experiment with new possibilities, take risks, and collaborate with remarkable people. We’ll look for you to bring your diverse perspectives, ideas, and skill-sets to make Prime Video even better for our customers. With global opportunities for talented technologists, you can decide where a career Prime Video Tech takes you! Key job responsibilities As an Applied Scientist in the Content Understanding Team, you will lead the end-to-end research and deployment of video and multi-modal models applied to a variety of downstream applications. More specifically, you will: - Work backwards from customer problems to research and design scientific approaches for solving them - Work closely with other scientists, engineers and product managers to expand the depth of our product insights with data, create a variety of experiments to determine the high impact projects to include in planning roadmaps - Stay up-to-date with advancements and the latest modeling techniques in the field - Publish your research findings in top conferences and journals About the team Our Prime Video Content Understanding team builds holistic media representations (e.g. descriptions of scenes, semantic embeddings) and apply them to new customer experiences supply chain problems. Our technology spans the entire Prime Video catalogue globally, and we enable instant recaps, skip intro timing, ad placement, search, and content moderation.
IN, HR, Gurugram
Our customers have immense faith in our ability to deliver packages timely and as expected. A well planned network seamlessly scales to handle millions of package movements a day. It has monitoring mechanisms that detect failures before they even happen (such as predicting network congestion, operations breakdown), and perform proactive corrective actions. When failures do happen, it has inbuilt redundancies to mitigate impact (such as determine other routes or service providers that can handle the extra load), and avoids relying on single points of failure (service provider, node, or arc). Finally, it is cost optimal, so that customers can be passed the benefit from an efficiently set up network. Amazon Shipping is hiring Applied Scientists to help improve our ability to plan and execute package movements. As an Applied Scientist in Amazon Shipping, you will work on multiple challenging machine learning problems spread across a wide spectrum of business problems. You will build ML models to help our transportation cost auditing platforms effectively audit off-manifest (discrepancies between planned and actual shipping cost). You will build models to improve the quality of financial and planning data by accurately predicting ship cost at a package level. Your models will help forecast the packages required to be pick from shipper warehouses to reduce First Mile shipping cost. Using signals from within the transportation network (such as network load, and velocity of movements derived from package scan events) and outside (such as weather signals), you will build models that predict delivery delay for every package. These models will help improve buyer experience by triggering early corrective actions, and generating proactive customer notifications. Your role will require you to demonstrate Think Big and Invent and Simplify, by refining and translating Transportation domain-related business problems into one or more Machine Learning problems. You will use techniques from a wide array of machine learning paradigms, such as supervised, unsupervised, semi-supervised and reinforcement learning. Your model choices will include, but not be limited to, linear/logistic models, tree based models, deep learning models, ensemble models, and Q-learning models. You will use techniques such as LIME and SHAP to make your models interpretable for your customers. You will employ a family of reusable modelling solutions to ensure that your ML solution scales across multiple regions (such as North America, Europe, Asia) and package movement types (such as small parcel movements and truck movements). You will partner with Applied Scientists and Research Scientists from other teams in US and India working on related business domains. Your models are expected to be of production quality, and will be directly used in production services. You will work as part of a diverse data science and engineering team comprising of other Applied Scientists, Software Development Engineers and Business Intelligence Engineers. You will participate in the Amazon ML community by authoring scientific papers and submitting them to Machine Learning conferences. You will mentor Applied Scientists and Software Development Engineers having a strong interest in ML. You will also be called upon to provide ML consultation outside your team for other problem statements. If you are excited by this charter, come join us!
US, MA, Boston
The Artificial General Intelligence (AGI) team is looking for a passionate, talented, and inventive Applied Scientist with a strong deep learning background, to build industry-leading technology with Large Language Models (LLMs) and multi-modal systems. You will support projects that work on technologies including multi-modal model alignment, moderation systems and evaluation. Key job responsibilities As an Applied Scientist with the AGI team, you will support the development of novel algorithms and modeling techniques, to advance the state of the art with LLMs. Your work will directly impact our customers in the form of products and services that make use of speech and language technology. You will leverage Amazon’s heterogeneous data sources and large-scale computing resources to accelerate advances in generative artificial intelligence (GenAI). You are also expected to publish in top tier conferences. About the team The AGI team has a mission to push the envelope in LLMs and multimodal systems. Specifically, we focus on model alignment with an aim to maintain safety while not denting utility, in order to provide the best-possible experience for our customers.
US, WA, Seattle
Do you want to re-invent how millions of people consume video content on their TVs, Tablets and Alexa? We are building a free to watch streaming service called Fire TV Channels (https://techcrunch.com/2023/08/21/amazon-launches-fire-tv-channels-app-400-fast-channels/). Our goal is to provide customers with a delightful and personalized experience for consuming content across News, Sports, Cooking, Gaming, Entertainment, Lifestyle and more. You will work closely with engineering and product stakeholders to realize our ambitious product vision. You will get to work with Generative AI and other state of the art technologies to help build personalization and recommendation solutions from the ground up. You will be in the driver's seat to present customers with content they will love. Using Amazon’s large-scale computing resources, you will ask research questions about customer behavior, build state-of-the-art models to generate recommendations and run these models to enhance the customer experience. You will participate in the Amazon ML community and mentor Applied Scientists and Software Engineers with a strong interest in and knowledge of ML. Your work will directly benefit customers and you will measure the impact using scientific tools.