GenAI RL & LLM Training Scientist

Amazon Inc.; Sunnyvale (CA); On-site; USD 172,000 - 222,000; Full time

Job summary

Amazon.com Services LLC is seeking an Applied Scientist with a strong deep learning background to help build training environments for language models. You will design RL gyms for LLM training, define tasks and rewards, and scale infrastructure to evaluate model progress.

You will work closely with model training teams to ensure environments maximize learning and transfer to real capabilities, shaping products that leverage generative AI.

Qualifications

• 3+ years building models for business applications
• PhD, or Master’s degree with 4+ years of CS/CE/ML experience
• Experience programming in Java, C++, Python or related language
• Experience in algorithms and data structures, parsing, numerical optimization, data mining, parallel and distributed computing, high-performance computing

Responsibilities

• Design, build, and evaluate reinforcement learning environments (RL gyms) for LLM training: realistic, verifiable task environments where models learn through interaction and feedback.
• Define tasks and reward signals, build the infrastructure to run environments at scale, measure how well environments transfer into model capability, and develop rigorous methods to verify environment quality and correctness.
• Work closely with model training teams to understand where environments are most valuable and iterate based on what the models learn.
• Your work will directly shape products and services that use generative AI.

Skills

RL awareness

Deep learning

Optimization concepts

Education

PhD or Master’s + 4+ years CS/CE/ML

Tools

Java

C++

Python

Job description

Amazon.com Services LLC is seeking an Applied Scientist with a strong deep learning background to help build training environments for language models. You will design RL gyms for LLM training, define tasks and rewards, and scale infrastructure to evaluate model progress.

You will work closely with model training teams to ensure environments maximize learning and transfer to real capabilities, shaping products that leverage generative AI.