Menlo Park, CA
All roles / Periodic Labs / Research Scientist, Scaling RL
Research Scientist, Scaling RL
Source verified: this exact posting was present on Periodic Labs’s careers feed on . View employer source →
The role
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.
Mechanics
Minimum 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.
Published by Periodic Labs on their own careers page and reproduced here unedited. Read it at Periodic Labs.
Apply at Periodic Labs → Applications go directly to Periodic Labs. This board does not sit in between, take a fee from you, or see your application.
What this listing does not tell you
Listed 8 days, which is recent for this board. Of the 40 post-training and RL roles this board has watched from listing to removal, 3% were gone from their employer's careers page by day 8, and the median came down after 110 days. That is a description of other listings that have already ended, not a prediction about this one: this board records when a listing disappears, never why, and a posting still up is not on a clock it can see.
Periodic Labs has 4 roles open on this board, 2 of them in post-training and RL.
Get the weekly AI Evals Jobs briefNew roles and board updates, with published pay where available. This is the general weekly brief. Or browse them all now.
Free. One email on Thursdays.
More roles like this
Matched by discipline, title, listed location and work arrangement.
Same discipline: Post-Training & RL · Shared listed location
Menlo Park, CA$250k – $350k+ equity
Same discipline: Post-Training & RL · Shared listed location
San Francisco$350k – $475k
Same discipline: Post-Training & RL
London, UK£375k – £640k
Same discipline: Post-Training & RL
London$250k – $535k+ equity
Same discipline: Post-Training & RL