Applied Scientist, AGI
Core
Design, build, and evaluate reinforcement learning environments (RL gyms) to teach large language models to reason, use tools, and complete complex multi-step tasks.
Role type
Applied Scientist (Reinforcement Learning & LLM Training)
Builds
Training environments for large language models
Domain
Generative AI, Large Language Models, Reinforcement Learning
Deliverable
production ML models
Required skills
deep learning, reinforcement learning, algorithms and data structures, numerical optimization, parallel and distributed computing, high-performance computing, Java, C++, Python
Preferred skills
Unix/Linux, professional software development
Technologies
Java, C++, Python
Responsibilities
Define tasks and reward signals for RL environments, build infrastructure to run environments at scale, measure environment transfer to model capability, develop methods to verify environment quality and correctness, iterate environments based on model learning feedback