Research Scientist Senior & levels

Responsibilities

Want to push the boundaries of what reinforcement learning can achieve with frontier models?

In this role you will be advancing reinforcement learning methods for large-scale AI systems. You’ll be applying RL techniques to enhance reasoning, planning, and decision‑making in models that directly impact fields from biology to climate and materials science.

Your work will combine RL with large language models, experimenting with RLHF, PPO, and DPO, designing evaluation frameworks, and fine‑tuning models  aim is to go beyond benchmarks and deliver models that researchers can use to accelerate discovery.

You will be a driving force in a team that is building towards a broader superintelligence platform: models that don’t just generate text or data, but drive breakthroughs across multiple domains. As part of this, you’ll collaborate with domain experts to ensure your research translates into real‑world scientific progress.

• Deep expertise in reinforcement learning (policy optimisation, value‑based, or model‑based methods).
• Experience applying RL to large models (RLHF, PPO, DPO).
• Hands‑on experience with model training and fine‑tuning at scale.
• PhD in Computer Science, Machine Learning, Robotics, or related field, with contributions to top‑tier conferences (NeurIPS, ICML, ICLR, AAAI).
• Experience with distributed computing platforms (cloud or HPC clusters).
• Track record of running rigorous experiments and improving models based on results.

If you have experience with multi‑agent RL, hierarchical/offline RL, or domain‑specific work with scientific datasets you will be an ideal candidate for this position.

Package: $250k - $400k base + bonus + stock

Location:

SF Bay area or potential for remote with travel to office when needed.

If you want to see your RL research power the next generation of superintelligence, this is the role for you!