Amazon and Energy Dept. team up to change how we recycle plastic

Amazon joins the US DOE’s Bio-Optimized Technologies to keep Thermoplastics out of Landfills and the Environment (BOTTLE™) Consortium, focusing on materials and recycling innovation.

Materials science probably does not come to mind when most people think of Amazon, but materials play a foundational role in almost everything we do. Materials often dictate what is possible in the physical world, from the thermal properties of materials used in our Echo devices to the fracture strength of lightweight structural materials used in our future low-Earth-orbit satellites.

Materials also play an outsized role in the area of sustainability. For example, global materials production contributes over 20% of all greenhouse gas (GHG) emissions, and over 75% of these emissions are generated from just four materials sectors: cement, steel, pulp and paper, and plastics.

Of all the materials used today, plastics are the fastest-growing category and offer the greatest opportunity for innovation. In joining the BOTTLE™ Consortium, led by the National Renewable Energy Laboratory (NREL), Amazon aims to help develop the foundational technologies that will enable the full life cycle of plastics to be net-zero carbon. From a scientific perspective, this requires rethinking plastics at the molecular level and developing new technologies that will keep these molecules in use.

Polyethylene.png
The repeating units of polyethylene polymer chains are characterized by strong carbon-carbon bonds.

Today, the most commonly used plastics are polyolefins, which include polyethylene and polypropylene, and the most common application for these materials is packaging. Recently, Raoul Meys and collaborators published an article in Science describing the feasibility of achieving net-zero, or even net-negative, carbon emissions for the full life cycle of these and other existing conventional plastics.

In this situation, the terms “net-zero” and “net-negative” mean that the sum of the total emissions associated with the life cycle of the material is zero or negative, respectively. This is possible when the carbon sequestered throughout the life cycle of the material, either from biomass feedstock or carbon capture technologies, equals or exceeds the total carbon emissions associated with materials production and end-of-life.

Based on the model Meys and collaborators developed, net-zero, or even slightly net-negative, carbon emissions are possible over the life cycle of plastics if we create a “circular carbon pathway” that combines mechanical recycling, chemical recycling with carbon capture, and feedstock derived from biomass and/or captured carbon. In essence, the carbon in the molecular backbone of these plastics should come from CO2 that is pulled out of the atmosphere (either through technological or biological means), and we should expand known recycling technologies that will keep the carbon in use as long as possible.

More on materials

Although the research by Meys and team shows a challenging yet feasible path toward net-zero carbon emissions for plastics, there are drawbacks to relying solely on existing commodity materials and known recycling technologies. The strong carbon-carbon bonds in polyolefins are difficult to break down, so in cases where mechanical recycling is not cost-effective — or even possible, due to contamination — energy-intensive chemical recycling processes (pyrolysis or gasification) would be required to recover and reuse the carbon. Likewise, conventional polyolefins with a carbon-carbon molecular backbone don’t break down easily in natural environments, an important consideration in cases where these materials may not make it into a recycling stream.

Amazon’s recent partnership with the BOTTLE (Bio-Optimized Technologies to keep Thermoplastics out of Landfills and the Environment) Consortium aims to help overcome some of these drawbacks and accelerate the path toward more-sustainable plastics.

Deconstructable waste

The goal of our work is to develop new technologies that will not only enable but also encourage keeping the carbon in plastics in use by ensuring it is both technically and economically viable to recover and recycle these materials at the end of their life. One objective of our work with the BOTTLE Consortium is to develop an energy-efficient chemical processing technology that can break down or deconstruct a mixed waste stream of plastics with labile bonds (i.e., bonds that are easy to deconstruct) into valuable feedstock that can be used to make the same types of plastics (closed-loop recycling) or new plastics altogether (open-loop recycling). And in the cases where these materials don’t make it into a future recycling stream, the molecular structure of these materials can be designed to biodegrade in natural environments.

AmazonScience_BOTTLE_RecyclingAnimation_1920x1080_V2.gif
New recycling methods can be used to deconstruct a mixed waste stream of polymers that are recyclable by design. The recycled molecules can then be used to make new materials without degraded properties.

By developing a new deconstruction technology that can handle a mixed waste stream of plastics, we will be eliminating the need for excessive sortation of the materials before deconstruction. This will also help accelerate scaling of the technology because of greater available-material volumes, and the technology itself will not be dependent on the commercial success of a single type of material.

An additional objective of the initial work we are doing with the BOTTLE Consortium is to develop new plastics that could be made from the chemicals coming out of this new deconstruction process. In some cases, closed-loop recycling may make the most sense. In other cases, developing new polymers from the deconstructed materials may be a better option.

Related content
A combination of deep learning, natural language processing, and computer vision enables Amazon to hone in on the right amount of packaging for each product.

Our plan is to synthesize new materials from the deconstructed plastics and process them into films to understand their structure-property relationships and then develop a path towards recyclable-by-design replacements for packaging applications, while also ensuring these materials could be composted in an industrial facility or safely degrade in natural environments.

We envision this new flexible deconstruction process as a flywheel, where the materials that require the least amount of time and energy to break down and recover will lead to lower-cost feedstock for new-materials production, leading to lower-cost materials. The lower costs of these materials will then further incentivize their use over traditional plastics. In addition, we anticipate that the materials that more easily break down in this new process will also have the added benefit of being more likely to be compostable or to easily degrade in natural environments.

Compostable recycling

This may lead to the question why. Why develop a new technology that can recycle plastics that can naturally degrade? Why not just help develop end-of-life pathways to compost those materials? There are two main reasons why we believe this is an important path to pursue.

Related content
New statistical model reduces shipment damage by 24% while cutting shipping costs by 5%.

The first is that we want to invent technologies that will ultimately incentivize the broad use of materials that can naturally degrade in the environment but are recycled because of their economic value as feedstock for new materials. This will reduce the need for additional feedstock for making new materials, which will reduce carbon emissions, while also ensuring plastics do not persist in the environment in the cases where they do not make it into a managed waste stream. This is not possible with conventional plastics but could be possible with new emerging plastics as the production and use of these materials grow, and new recycling technologies are developed.

The second reason is that these new emerging plastics have the potential to enable a more efficient recycling system. Plastics that are biodegradable, either in a compost pile or in the natural environment, are fundamentally easier to deconstruct into intermediate chemicals than conventional plastics are. This opens the possibility for efficient processes that can infinitely recycle the carbon molecules in these materials without degradation of properties (e.g., mechanical recycling) or the substantial amounts of energy needed to deconstruct strong carbon-carbon bonds (e.g., pyrolysis).

Ultimately, the success of this work at scale will require a fundamental shift in both the plastics that are used in our everyday lives, especially plastics used in applications such as food packaging, and the recycling systems and infrastructure to keep these materials in use. Effecting that shift is a daunting task. But knowing that Amazon started out as an online bookstore serving customers out of a garage provides hope that even daunting tasks are achievable.

Research areas

Related content

US, MA, Boston
The Artificial General Intelligence (AGI) team is seeking a dedicated, skilled, and innovative Applied Scientist with a robust background in machine learning, statistics, quality assurance, auditing methodologies, and automated evaluation systems to ensure the highest standards of data quality, to build industry-leading technology with Large Language Models (LLMs) and multimodal systems. Key job responsibilities As part of the AGI team, an Applied Scientist will collaborate closely with core scientist team developing Amazon Nova models. They will lead the development of comprehensive quality strategies and auditing frameworks that safeguard the integrity of data collection workflows. This includes designing auditing strategies with detailed SOPs, quality metrics, and sampling methodologies that help Nova improve performances on benchmarks. The Applied Scientist will perform expert-level manual audits, conduct meta-audits to evaluate auditor performance, and provide targeted coaching to uplift overall quality capabilities. A critical aspect of this role involves developing and maintaining LLM-as-a-Judge systems, including designing judge architectures, creating evaluation rubrics, and building machine learning models for automated quality assessment. The Applied Scientist will also set up the configuration of data collection workflows and communicate quality feedback to stakeholders. An Applied Scientist will also have a direct impact on enhancing customer experiences through high-quality training and evaluation data that powers state-of-the-art LLM products and services. A day in the life An Applied Scientist with the AGI team will support quality solution design, conduct root cause analysis on data quality issues, research new auditing methodologies, and find innovative ways of optimizing data quality while setting examples for the team on quality assurance best practices and standards. Besides theoretical analysis and quality framework development, an Applied Scientist will also work closely with talented engineers, domain experts, and vendor teams to put quality strategies and automated judging systems into practice.
US, MA, Boston
The Artificial General Intelligence (AGI) team is seeking a dedicated, skilled, and innovative Applied Scientist with a robust background in machine learning, statistics, quality assurance, auditing methodologies, and automated evaluation systems to ensure the highest standards of data quality, to build industry-leading technology with Large Language Models (LLMs) and multimodal systems. Key job responsibilities As part of the AGI team, an Applied Scientist will collaborate closely with core scientist team developing Amazon Nova models. They will lead the development of comprehensive quality strategies and auditing frameworks that safeguard the integrity of data collection workflows. This includes designing auditing strategies with detailed SOPs, quality metrics, and sampling methodologies that help Nova improve performances on benchmarks. The Applied Scientist will perform expert-level manual audits, conduct meta-audits to evaluate auditor performance, and provide targeted coaching to uplift overall quality capabilities. A critical aspect of this role involves developing and maintaining LLM-as-a-Judge systems, including designing judge architectures, creating evaluation rubrics, and building machine learning models for automated quality assessment. The Applied Scientist will also set up the configuration of data collection workflows and communicate quality feedback to stakeholders. An Applied Scientist will also have a direct impact on enhancing customer experiences through high-quality training and evaluation data that powers state-of-the-art LLM products and services. A day in the life An Applied Scientist with the AGI team will support quality solution design, conduct root cause analysis on data quality issues, research new auditing methodologies, and find innovative ways of optimizing data quality while setting examples for the team on quality assurance best practices and standards. Besides theoretical analysis and quality framework development, an Applied Scientist will also work closely with talented engineers, domain experts, and vendor teams to put quality strategies and automated judging systems into practice.
US, MA, Boston
The Artificial General Intelligence (AGI) team is seeking a dedicated, skilled, and innovative Applied Scientist with a robust background in machine learning, statistics, quality assurance, auditing methodologies, and automated evaluation systems to ensure the highest standards of data quality, to build industry-leading technology with Large Language Models (LLMs) and multimodal systems. Key job responsibilities As part of the AGI team, an Applied Scientist will collaborate closely with core scientist team developing Amazon Nova models. They will lead the development of comprehensive quality strategies and auditing frameworks that safeguard the integrity of data collection workflows. This includes designing auditing strategies with detailed SOPs, quality metrics, and sampling methodologies that help Nova improve performances on benchmarks. The Applied Scientist will perform expert-level manual audits, conduct meta-audits to evaluate auditor performance, and provide targeted coaching to uplift overall quality capabilities. A critical aspect of this role involves developing and maintaining LLM-as-a-Judge systems, including designing judge architectures, creating evaluation rubrics, and building machine learning models for automated quality assessment. The Applied Scientist will also set up the configuration of data collection workflows and communicate quality feedback to stakeholders. An Applied Scientist will also have a direct impact on enhancing customer experiences through high-quality training and evaluation data that powers state-of-the-art LLM products and services. A day in the life An Applied Scientist with the AGI team will support quality solution design, conduct root cause analysis on data quality issues, research new auditing methodologies, and find innovative ways of optimizing data quality while setting examples for the team on quality assurance best practices and standards. Besides theoretical analysis and quality framework development, an Applied Scientist will also work closely with talented engineers, domain experts, and vendor teams to put quality strategies and automated judging systems into practice.
US, WA, Bellevue
The Artificial General Intelligence (AGI) team is seeking a dedicated, skilled, and innovative Applied Scientist with a robust background in machine learning, statistics, quality assurance, auditing methodologies, and automated evaluation systems to ensure the highest standards of data quality, to build industry-leading technology with Large Language Models (LLMs) and multimodal systems. Key job responsibilities As part of the AGI team, an Applied Scientist will collaborate closely with core scientist team developing Amazon Nova models. They will lead the development of comprehensive quality strategies and auditing frameworks that safeguard the integrity of data collection workflows. This includes designing auditing strategies with detailed SOPs, quality metrics, and sampling methodologies that help Nova improve performances on benchmarks. The Applied Scientist will perform expert-level manual audits, conduct meta-audits to evaluate auditor performance, and provide targeted coaching to uplift overall quality capabilities. A critical aspect of this role involves developing and maintaining LLM-as-a-Judge systems, including designing judge architectures, creating evaluation rubrics, and building machine learning models for automated quality assessment. The Applied Scientist will also set up the configuration of data collection workflows and communicate quality feedback to stakeholders. An Applied Scientist will also have a direct impact on enhancing customer experiences through high-quality training and evaluation data that powers state-of-the-art LLM products and services. A day in the life An Applied Scientist with the AGI team will support quality solution design, conduct root cause analysis on data quality issues, research new auditing methodologies, and find innovative ways of optimizing data quality while setting examples for the team on quality assurance best practices and standards. Besides theoretical analysis and quality framework development, an Applied Scientist will also work closely with talented engineers, domain experts, and vendor teams to put quality strategies and automated judging systems into practice.
US, MA, Boston
The Artificial General Intelligence (AGI) team is seeking a dedicated, skilled, and innovative Applied Scientist with a robust background in machine learning, statistics, quality assurance, auditing methodologies, and automated evaluation systems to ensure the highest standards of data quality, to build industry-leading technology with Large Language Models (LLMs) and multimodal systems. Key job responsibilities As part of the AGI team, an Applied Scientist will collaborate closely with core scientist team developing Amazon Nova models. They will lead the development of comprehensive quality strategies and auditing frameworks that safeguard the integrity of data collection workflows. This includes designing auditing strategies with detailed SOPs, quality metrics, and sampling methodologies that help Nova improve performances on benchmarks. The Applied Scientist will perform expert-level manual audits, conduct meta-audits to evaluate auditor performance, and provide targeted coaching to uplift overall quality capabilities. A critical aspect of this role involves developing and maintaining LLM-as-a-Judge systems, including designing judge architectures, creating evaluation rubrics, and building machine learning models for automated quality assessment. The Applied Scientist will also set up the configuration of data collection workflows and communicate quality feedback to stakeholders. An Applied Scientist will also have a direct impact on enhancing customer experiences through high-quality training and evaluation data that powers state-of-the-art LLM products and services. A day in the life An Applied Scientist with the AGI team will support quality solution design, conduct root cause analysis on data quality issues, research new auditing methodologies, and find innovative ways of optimizing data quality while setting examples for the team on quality assurance best practices and standards. Besides theoretical analysis and quality framework development, an Applied Scientist will also work closely with talented engineers, domain experts, and vendor teams to put quality strategies and automated judging systems into practice.
US, MA, Boston
The Artificial General Intelligence (AGI) team is seeking a dedicated, skilled, and innovative Applied Scientist with a robust background in machine learning, statistics, quality assurance, auditing methodologies, and automated evaluation systems to ensure the highest standards of data quality, to build industry-leading technology with Large Language Models (LLMs) and multimodal systems. Key job responsibilities As part of the AGI team, an Applied Scientist will collaborate closely with core scientist team developing Amazon Nova models. They will lead the development of comprehensive quality strategies and auditing frameworks that safeguard the integrity of data collection workflows. This includes designing auditing strategies with detailed SOPs, quality metrics, and sampling methodologies that help Nova improve performances on benchmarks. The Applied Scientist will perform expert-level manual audits, conduct meta-audits to evaluate auditor performance, and provide targeted coaching to uplift overall quality capabilities. A critical aspect of this role involves developing and maintaining LLM-as-a-Judge systems, including designing judge architectures, creating evaluation rubrics, and building machine learning models for automated quality assessment. The Applied Scientist will also set up the configuration of data collection workflows and communicate quality feedback to stakeholders. An Applied Scientist will also have a direct impact on enhancing customer experiences through high-quality training and evaluation data that powers state-of-the-art LLM products and services. A day in the life An Applied Scientist with the AGI team will support quality solution design, conduct root cause analysis on data quality issues, research new auditing methodologies, and find innovative ways of optimizing data quality while setting examples for the team on quality assurance best practices and standards. Besides theoretical analysis and quality framework development, an Applied Scientist will also work closely with talented engineers, domain experts, and vendor teams to put quality strategies and automated judging systems into practice.
US, MA, Boston
The Artificial General Intelligence (AGI) team is seeking a dedicated, skilled, and innovative Applied Scientist with a robust background in machine learning, statistics, quality assurance, auditing methodologies, and automated evaluation systems to ensure the highest standards of data quality, to build industry-leading technology with Large Language Models (LLMs) and multimodal systems. Key job responsibilities As part of the AGI team, an Applied Scientist will collaborate closely with core scientist team developing Amazon Nova models. They will lead the development of comprehensive quality strategies and auditing frameworks that safeguard the integrity of data collection workflows. This includes designing auditing strategies with detailed SOPs, quality metrics, and sampling methodologies that help Nova improve performances on benchmarks. The Applied Scientist will perform expert-level manual audits, conduct meta-audits to evaluate auditor performance, and provide targeted coaching to uplift overall quality capabilities. A critical aspect of this role involves developing and maintaining LLM-as-a-Judge systems, including designing judge architectures, creating evaluation rubrics, and building machine learning models for automated quality assessment. The Applied Scientist will also set up the configuration of data collection workflows and communicate quality feedback to stakeholders. An Applied Scientist will also have a direct impact on enhancing customer experiences through high-quality training and evaluation data that powers state-of-the-art LLM products and services. A day in the life An Applied Scientist with the AGI team will support quality solution design, conduct root cause analysis on data quality issues, research new auditing methodologies, and find innovative ways of optimizing data quality while setting examples for the team on quality assurance best practices and standards. Besides theoretical analysis and quality framework development, an Applied Scientist will also work closely with talented engineers, domain experts, and vendor teams to put quality strategies and automated judging systems into practice.
US, MA, Boston
The Artificial General Intelligence (AGI) team is seeking a dedicated, skilled, and innovative Applied Scientist with a robust background in machine learning, statistics, quality assurance, auditing methodologies, and automated evaluation systems to ensure the highest standards of data quality, to build industry-leading technology with Large Language Models (LLMs) and multimodal systems. Key job responsibilities As part of the AGI team, an Applied Scientist will collaborate closely with core scientist team developing Amazon Nova models. They will lead the development of comprehensive quality strategies and auditing frameworks that safeguard the integrity of data collection workflows. This includes designing auditing strategies with detailed SOPs, quality metrics, and sampling methodologies that help Nova improve performances on benchmarks. The Applied Scientist will perform expert-level manual audits, conduct meta-audits to evaluate auditor performance, and provide targeted coaching to uplift overall quality capabilities. A critical aspect of this role involves developing and maintaining LLM-as-a-Judge systems, including designing judge architectures, creating evaluation rubrics, and building machine learning models for automated quality assessment. The Applied Scientist will also set up the configuration of data collection workflows and communicate quality feedback to stakeholders. An Applied Scientist will also have a direct impact on enhancing customer experiences through high-quality training and evaluation data that powers state-of-the-art LLM products and services. A day in the life An Applied Scientist with the AGI team will support quality solution design, conduct root cause analysis on data quality issues, research new auditing methodologies, and find innovative ways of optimizing data quality while setting examples for the team on quality assurance best practices and standards. Besides theoretical analysis and quality framework development, an Applied Scientist will also work closely with talented engineers, domain experts, and vendor teams to put quality strategies and automated judging systems into practice.
GB, London
As a STRUC Economist Intern, you'll specialize in structural econometric analysis to estimate fundamental preferences and strategic effects in complex business environments. Your responsibilities include: Analyze large-scale datasets using structural econometric techniques to solve complex business challenges Applying discrete choice models and methods, including logistic regression family models (such as BLP, nested logit) and models with alternative distributional assumptions Utilizing advanced structural methods including dynamic models of customer or firm decisions over time, applied game theory (entry and exit of firms), auction models, and labor market models Building datasets and performing data analysis at scale Collaborating with economists, scientists, and business leaders to develop data-driven insights and strategic recommendations Tackling diverse challenges including pricing analysis, competition modeling, strategic behavior estimation, contract design, and marketing strategy optimization Helping business partners formalize and estimate business objectives to drive optimal decision-making and customer value Build and refine comprehensive datasets for in-depth structural economic analysis Present complex analytical findings to business leaders and stakeholders
US, WA, Seattle
At Amazon Selection and Catalog Systems (ASCS), our mission is to power the online buying experience for customers worldwide so they can find, discover, and buy any product they want. We innovate on behalf of our customers to ensure uniqueness and consistency of product identity and to infer relationships between products in Amazon Catalog to drive the selection gateway for the search and browse experiences on the website. We're solving a fundamental AI challenge: establishing product identity and relationships at unprecedented scale. Using Generative AI, Visual Language Models (VLMs), and multimodal reasoning, we determine what makes each product unique and how products relate to one another across Amazon's catalog. The scale is staggering: billions of products, petabytes of multimodal data, millions of sellers, dozens of languages, and infinite product diversity—from electronics to groceries to digital content. The research challenges are immense. GenAI and VLMs hold transformative promise for catalog understanding, but we operate where traditional methods fail: ambiguous problem spaces, incomplete and noisy data, inherent uncertainty, reasoning across both images and textual data, and explaining decisions at scale. Establishing product identities and groupings requires sophisticated models that reason across text, images, and structured data—while maintaining accuracy and trust for high-stakes business decisions affecting millions of customers daily. Amazon's Item and Relationship Platform group is looking for an innovative and customer-focused applied scientist to help us make the world's best product catalog even better. In this role, you will partner with technology and business leaders to build new state-of-the-art algorithms, models, and services to infer product-to-product relationships that matter to our customers. You will pioneer advanced GenAI solutions that power next-generation agentic shopping experiences, working in a collaborative environment where you can experiment with massive data from the world's largest product catalog, tackle problems at the frontier of AI research, rapidly implement and deploy your algorithmic ideas at scale, across millions of customers. Key job responsibilities Key job responsibilities include: * Formulate novel research problems at the intersection of GenAI, multimodal learning, and large-scale information retrieval—translating ambiguous business challenges into tractable scientific frameworks * Design and implement leading models leveraging VLMs, foundation models, and agentic architectures to solve product identity, relationship inference, and catalog understanding at billion-product scale * Pioneer explainable AI methodologies that balance model performance with scalability requirements for production systems impacting millions of daily customer decisions * Design and execute model distillation strategies—distilling large frontier LLMs and VLMs into compact, production-grade models—that preserve multimodal reasoning capability while dramatically reducing serving latency, cost, and infrastructure footprint at billion-product catalog scale * Own end-to-end ML pipelines from research ideation to production deployment—processing petabytes of multimodal data with rigorous evaluation frameworks * Define research roadmaps aligned with business priorities, balancing foundational research with incremental product improvements * Mentor peer scientists and engineers on advanced ML techniques, experimental design, and scientific rigor—building organizational capability in GenAI and multimodal AI * Represent the team in the broader science community—publishing findings, delivering tech talks, and staying at the forefront of GenAI, VLM, and agentic system research