Staff Research Scientist - Reinforcement Learning

What you'll do

• Design simulation environments, digital twins, agent learning loops, training-data pipelines, reward functions, and verifiers.
• Set technical direction and engineering standards; review code and mentor researchers and engineers.
• Translate research into production systems and contribute to publications.

What they ask for

• 7+ years in ML/AI research or engineering, including 3+ years at senior/staff level; 5+ years hands-on RL, including a production deployment.
• MS or PhD in Computer Science, Machine Learning, or a related field (or equivalent).
• 3+ years fine-tuning LLMs with hands-on RL post-training; expert-level implementation of RLHF pipelines, reward modeling (Bradley-Terry), DPO, and KTO.
• Strong Python and software engineering skills; deep expertise in MDPs, policy gradient methods, and temporal difference learning; hands-on Gymnasium environment and reward-engineering experience.

Nice to have

• Publications at NeurIPS, ICML, ICLR, ACL, COLM, or similar venues; open-source contributions to post-training or agent frameworks.
• Experience with Offline RL, Model-based RL / World Models, Hierarchical RL, synthetic data, simulation, domain areas listed, or distributed GPU-cluster training.

Pay

$200k-$250k (USD, base salary)

Tools

RLHF, DPO, GRPO, PPO, KTO, TRL, veRL, OpenRLHF

AI focus

LLM agent post-training with reinforcement learning, reward modeling, simulation, and tool-using agent development.