Research Scientist, Scaling RL
Join Periodic Labs as a Research Scientist to advance reinforcement learning algorithms and scale scientific models.
Posted by employer 17 hours ago
First seen on Joblaze 13 hours ago
Last verified on the company career page 13 hours ago
Skills & Technologies
What you'll build
- Design experiments to understand RL performance scaling
- Develop better RL algorithms
- Build adaptive sampling and curriculum methods
- Study bias and stability during RL training
- Improve compute efficiency across training and inference
Must have
- Hands-on experience training LLMs with reinforcement learning
- Strong attention to detail
- Experience with small-scale RL setups
Nice to have
- Comfort working across a complex training stack
AI in the day-to-day
We're training frontier models to develop deep scientific knowledge and reasoning for scientific tasks.
Requirements
- Experience
- 5+ years
- Education
- Bachelor's degree
- Visa
- Sponsorship available
Not disclosed in this posting: work arrangement.
Benefits
Joblaze summary
In this role, the Research Scientist focuses on designing and conducting experiments to analyze how reinforcement learning (RL) performance scales with various factors such as compute and model size. Key skills include hands-on experience with training large language models using RL, along with a strong grasp of algorithm development and adaptive sampling techniques. This position is ideal for someone with over five years of experience who can navigate complex training stacks and apply rigorous scientific methods. Periodic Labs is a rapidly growing AI and physical sciences company, emphasizing innovation in scientific modeling.
Joblaze insights
- Listed today — first seen on Joblaze October 1, 2026. Last confirmed on Periodic Labs's careers page October 1, 2026.
- Salary band is above the typical range for AI/ML roles (median ~$190,000).
- Starts above 73% of 70 comparable senior ai/ml roles in United States that list Machine Learning we track (median $207,727 across 34 companies). See Machine Learning salary trends
- Machine Learning appears in 19.6% of 536 comparable senior ai/ml roles in United States; reinforcement learning appears in 6% of 536 comparable senior ai/ml roles in United States.
Quick facts
- What's the salary range?
- Periodic Labs lists $250,000–$350,000 for this role.
- How much experience is required?
- At least 5 years of relevant experience for this Research Scientist, Scaling RL role.
- What's the tech stack?
- Joblaze extracted these technologies from the posting: Machine Learning, reinforcement learning.
- Does Periodic Labs sponsor work visas for this role?
- Yes — the posting indicates visa sponsorship is available for the right candidate.
- What seniority level is this role?
- Periodic Labs targets senior candidates for this position.
- Is this full-time or contract?
- Full-time for this Research Scientist, Scaling RL role at Periodic Labs.
From the original posting
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.
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 experience: 5+ years
Minimum education: Bachelor’s degree or similar experience
Location: Menlo Park, CA
Compensation: $250,000-$350,000 base + equity
Visa sponsorship: Yes, we sponsor visas and will do everything we can to assist in this process.
Standard company text repeated across Periodic Labs's postings is omitted here.