Staff Research Scientist / Reinforcement Learning

Title: Staff Research Leader
Location: San Jose, CA
Salary: $250K-$350K + Equity

A cutting-edge AI company is hiring a Staff AI Researcher to lead a small team while remaining hands-on across reinforcement learning and LLM post-training. This is a role where researchers take ownership over their work, collaborate closely with leadership, and help shape the technical direction of the organization. The ideal candidate enjoys mentoring junior researchers while continuing to contribute individually to cutting-edge RL research and implementation.

This role is focused on advancing LLM performance through RLHF and modern post-training techniques. You will build and improve RLHF pipelines, develop reward models, and design post-training workflows using approaches such as PPO, DPO, GRPO, KTO, and similar methods. You'll work closely with evaluation frameworks to identify model weaknesses, build reinforcement learning environments, and translate research into production-ready improvements. This role is ideal for someone with hands-on experience fine-tuning frontier models, publishing RL research, and leading technical initiatives in a collaborative research environment.

Experience:

* 5+ years of experience in AI Research, Applied Research, or Machine Learning
* PhD in Computer Science, Machine Learning, or a related technical field preferred
* 3+ years of experience fine-tuning LLMs using RLHF, PPO, DPO, GRPO, or similar post-training methods
* Experience building reinforcement learning environments, evaluation frameworks, and benchmark-driven systems
* Experience with modern post-training libraries such as TRL, OpenRLHF, veRL, SkyRL, or similar
* Strong publication record at ICML, NeurIPS, ICLR, ACL, or similar conferences preferred
* Experience mentoring researchers or leading technical initiatives while remaining hands-on
* Strong Python experience implementing machine learning research into production systems

Benefits:

* Equity
* Paid Time Off
* Medical, dental, and vision coverage
* Opportunity to create lasting impact within a growing organization
* Opportunity to lead and grow a high-performing research team
* Hybrid working schedule

Oscar Associates Limited (US) is acting as an Employment Agency in relation to this vacancy.