Senior Applied Scientist, LLM Code Agents, Kiro Science

Saved job description

One of the key bottlenecks in training capable code agents today is the environment the model is trained on. You can't RL your way to a better coding agent if your training rollouts are running against environments that don't actually reflect how software gets built, have flaky rewards, are prone to reward hacking, or rely on unreliable verification methodology.

We're building and improving 𝗞𝗶𝗿𝗼 — Amazon's next-gen AI coding agent — and we're building 𝘃𝗲𝗿𝗶𝗳𝗶𝗲𝗱 (𝗲𝘅𝗲𝗰𝘂𝘁𝗶𝗼𝗻-𝗯𝗮𝘀𝗲𝗱 𝗼𝗿 𝗻𝗲𝘂𝗿𝗼𝘀𝘆𝗺𝗯𝗼𝗹𝗶𝗰) 𝗥𝗟 𝗲𝗻𝘃𝗶𝗿𝗼𝗻𝗺𝗲𝗻𝘁𝘀 𝗮𝘁 𝘀𝗰𝗮𝗹𝗲.

We're looking for someone excited about the problem. The strongest candidates have depth in at least one of:

𝗣𝗿𝗼𝗴𝗿𝗮𝗺𝗺𝗶𝗻𝗴 𝗟𝗮𝗻𝗴𝘂𝗮𝗴𝗲𝘀 / 𝗦𝗘 — type systems, compilers, build systems, dependency analysis, program analysis

𝗔𝗽𝗽𝗹𝗶𝗲𝗱 𝗟𝗟𝗠𝘀 𝗮𝗻𝗱 T𝗿𝗮𝗶𝗻𝗶𝗻𝗴 — post-training, RLHF / RLVR / RLAIF, distillation, evaluation harnesses, agent scaffolds

𝗥𝗟 𝗚𝘆𝗺 𝗱𝗲𝘃𝗲𝗹𝗼𝗽𝗺𝗲𝗻𝘁 — Gymnasium, custom verifiers, reward design, sandboxing

𝗦𝗼𝗳𝘁𝘄𝗮𝗿𝗲 𝗘𝗻𝗴𝗶𝗻𝗲𝗲𝗿𝗶𝗻𝗴 𝗮𝘁 𝘀𝗰𝗮𝗹𝗲 — containerization, deterministic execution, CI/CD systems, hermetic builds

Key job responsibilities

𝗪𝗵𝗮𝘁 𝘆𝗼𝘂'𝗹𝗹 𝘄𝗼𝗿𝗸 𝗼𝗻:

• Designing verified RL environments built from real codebases and post training with these environments

• Reward functions that survive Goodhart's law on F2P / P2P / mutation tests

• Scaling environment generation pipelines that stay fresh against contamination

• Publishing at NeurIPS / ICML / ICLR / ICSE / OOPSLA / ACL

About the team

The AWS Developer Agents and Experiences (DAE) team is reimagining the builder experience through generative AI and foundation models. We're leveraging the latest advances in AI to transform how engineers work from IDE environments to web-based tools and services, empowering developers to tackle projects of any scale with unprecedented efficiency.

Broadly, AWS Utility Computing (UC) provides product innovations — from foundational services such as Amazon’s Simple Storage Service (S3) and Amazon Elastic Compute Cloud (EC2), to consistently released new product innovations that continue to set AWS’s services and features apart in the industry. As a member of the UC organization, you’ll support the development and management of Compute, Database, Storage, Internet of Things (Iot), Platform, and Productivity Apps services in AWS. Within AWS UC, Amazon Dedicated Cloud (ADC) roles engage with AWS customers who require specialized security solutions for their cloud services.

Why AWS?

Amazon Web Services (AWS) is the world’s most comprehensive and broadly adopted cloud platform. We pioneered cloud computing and never stopped innovating — that’s why customers from the most successful startups to Global 500 companies trust our robust suite of products and services to power their businesses.

Inclusive Team Culture

Here at AWS, it’s in our nature to learn and be curious. Our employee-led affinity groups foster a culture of inclusion that empower us to be proud of our differences. Ongoing events and learning experiences, including our Conversations on Race and Ethnicity (CORE) and AmazeCon conferences, inspire us to never stop embracing our uniqueness.

Mentorship & Career Growth

We’re continuously raising our performance bar as we strive to become Earth’s Best Employer. That’s why you’ll find endless knowledge-sharing, mentorship and other career-advancing resources here to help you develop into a better-rounded professional.

Work/Life Balance

We value work-life harmony. Achieving success at work should never come at the expense of sacrifices at home, which is why we strive for flexibility as part of our working culture. When we feel supported in the workplace and at home, there’s nothing we can’t achieve in the cloud.

Hybrid Work

We value innovation and recognize this sometimes requires uninterrupted time to focus on a build. We also value in-person collaboration and time spent face-to-face. Our team affords employees options to work in the office every day or in a flexible, hybrid work model near one of our U.S. Amazon offices.

Requirements: - 3+ years of building machine learning models for business 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