Digital Agency, Web Development, Software Development, Consulting

Research Scientist, Scaling RL

Menlo ParkFull Time$225,000–$350,000 /yrPosted 1 month ago

Is this role right for you?

Upload your resume and get a skill-by-skill breakdown — see exactly where you match, where you're close, and what to highlight. Not a mystery percentage.

Get a tailored resume highlighting what this role needs.

Required skills

Reinforcement Learning
LLMs
scaling
compute
model size
data
reward quality
policy optimization
advantage estimation
exploration

Nice to have

materials science
energy
physical sciences
frontier models
scientific knowledge
scientific reasoning

Role summary

Periodic Labs is an AI and physical sciences company seeking a Research Scientist specializing in Scaling Reinforcement Learning (RL). This role involves designing experiments to understand RL scaling with compute, model size, and data, developing advanced RL algorithms, and building adaptive sampling and curriculum methods. You will also study training stability and improve compute efficiency. The ideal candidate has hands-on experience training LLMs with RL, a rigorous scientific approach, and the ability to transfer small-scale RL setups to large-scale training. A Bachelor's degree or equivalent experience and 5+ years of relevant experience are required. The position is based in Menlo Park, CA.

About Periodic Labs

We're an AI and physical sciences company building state-of-the-art models to accelerate breakthroughs across materials, energy, and beyond. Backed by world-class investors and growing rapidly, we operate at the pace the frontier requires. Our team brings deep expertise, genuine ownership, and a drive to push the boundaries of what's scientifically possible.

About the Role

We're training frontier models to develop deep scientific knowledge and reasoning for scientific tasks. You’ll study how RL scales with training compute, develop better algorithms, and take ideas from controlled experiments to our largest runs like Periodic Neon.

What You'll Do

Design experiments to understand how RL performance scales with compute, model size, data, and reward quality, building on work such as ScaleRL
Develop better RL algorithms, spanning policy optimization, advantage estimation, exploration, and credit assignment for long-horizon RL tasks
Build adaptive sampling and curriculum methods that adjust task difficulty, problem selection, and the number of rollouts as models improve
Study bias and stability during RL training, including importance-sampling corrections and methods to tackle policy staleness and training–inference mismatch, as discussed here.
Improve compute efficiency across training and inference through experiments with hyperparameters, such as length penalties, rollout counts, batch sizes, and update schedules.

You Will Thrive in This Role If You Have

Hands-on experience training LLMs with reinforcement learning
Strong attention to detail and rigorous approach to answer questions scientifically.
Coming up with small-scale RL setups that transfers to large-scale training runs.
Comfort working across a complex training stack to implement, debug, and test new research ideas.
We are open to offering a 1 year post-doc for this profile. Early career (final year PhD students) are encouraged to apply.

MechanicsMinimum education: Bachelor’s degree or similar experience

Location: Menlo Park, CA or Montreal, Canada

Compensation: $225,000-$350,000 base + equity

Visa sponsorship: Yes, we sponsor visas and will do everything we can to assist in this process.

Ready to apply?

You'll be redirected to Periodic Labs's application page.