About the Role
Join an early-stage AI team as a Founding Reinforcement Learning Engineer, building core systems for training and evaluating AI agents. You will own the process from environment design through model training and evaluation, and help shape the team's technical direction.
What You'll Do
Design and build reinforcement learning environments, reward functions, and training pipelines.
Train and fine-tune models using methods such as PPO, GRPO, DPO, RLHF, and RLAIF.
Build evaluation frameworks to measure model and agent performance.
Run experiments, analyze results, and guide research priorities.
Scale training across GPU clusters and maintain reliable pipelines.
Bring research ideas into production systems and help establish engineering practices.
Contribute to hiring as the engineering team grows.
What We're Looking For
At least 2 years of hands-on experience in reinforcement learning or machine learning engineering.
Strong Python skills and deep experience with PyTorch or JAX.
Practical experience training models with policy gradient methods, reward modeling, RLHF, or similar techniques.
Experience with distributed training, GPU infrastructure, RL environments, reward functions, training pipelines, and model or agent evaluation.
A track record of turning research ideas into production systems.
A degree in computer science, mathematics, physics, or a related field; graduate study is a plus.
Experience with LLM post-training, agent training, simulation frameworks, or RL training libraries is a plus.
Compensation & Benefits
Compensation is $125,000 to $200,000 USD annually. Visa sponsorship is available.
Location
This is an on-site role in San Francisco, California, United States.