Member of Engineering (Reinforcement Learning)
Core
Research and implement reinforcement learning to improve reasoning and coding capabilities of Large Language Models.
Role type
Senior IC reinforcement learning engineer (LLM reasoning)
Builds
RL training pipelines and environments for foundational models
Domain
Artificial Intelligence / Large Language Models / Reinforcement Learning
Deliverable
production ML models
Required skills
Reinforcement Learning algorithms, Large Language Models, Transformer architecture, distributed training, Python, deep learning frameworks (PyTorch/JAX), experiment lifecycle management
Preferred skills
Scientific publications in RL/LLMs, agentic model training
Technologies
PyTorch, JAX, Python
Responsibilities
Research and experiment on improving reasoning and code generation for LLMs, design and scale RL environments, implement RL training pipelines, diagnose training instabilities, write reproducible code
Seniority
Senior, hands-on IC