research scientist - RL

Cerebro; San Francisco (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

Cerebro, a leading applied AI research lab in San Francisco, seeks an AI Research Scientist focused on reinforcement learning to push the frontiers of RL techniques and their use with large models.

You will develop optimization-based methods for automated RL environment generation, establish baselines for environment quality, design infrastructure for dynamic environments from historical data and agent evaluations, and drive your own research agenda.

Qualifications

• PhD (or equivalent) in machine learning, computer science or a related field.
• Strong publication record and/or evidence of research impact (open source, deployed systems, etc.).
• Deep expertise in reinforcement learning and machine learning fundamentals.

Responsibilities

• Develop novel optimization-based methods for automated RL environment generation.
• Establish baselines for evaluating the quality and diversity of RL environments.
• Design infrastructure to create dynamic environments from historical datasets and agent evaluations.
• Drive your own research agenda, contributing directly to the progress of our platform and the broader AI community.

Skills

Python proficiency

RL expertise

Education

PhD or equivalent experience

Tools

PyTorch

JAX

Job description

Join a Leading Applied Research Lab Pushing the Boundaries of Reinforcement Learning

Are you passionate about advancing the frontiers of reinforcement learning (RL)? An innovative AI research lab is seeking talented and ambitious scientists to shape the next generation of RL techniques—especially where they intersect with large models and environment generation.

About the Role

As an AI Research Scientist focused on RL, you will:

• Develop novel optimization-based methods for automated RL environment generation


• Establish baselines for evaluating the quality and diversity of RL environments


• Design infrastructure to create dynamic environments from historical datasets and agent evaluations


• Drive your own research agenda, contributing directly to the progress of our platform and the broader AI community

What We’re Looking For

• PhD (or equivalent experience) in machine learning, computer science or a related field


• Strong publication record and/or evidence of research impact (open source, deployed systems, etc.)


• Deep expertise in reinforcement learning and machine learning fundamentals


• Proficient in Python and at least one modern ML framework (such as PyTorch or JAX)

Bonus Points

• Experience with post-training large language models (LLMs)


• Demonstrated software engineering skills


• Ability to communicate research findings effectively to both technical and non-technical audiences