Base Labs Research Scientist - RL Environments
Baseten · San Francisco · New York
Infrastructureremote$210k–$285k
At a glance
Highlights
- Create open RL environments and study how models learn from them.
- Design task distributions, rewards and verifiers that test real capabilities.
- Run RL experiments to measure learning, curricula and transfer to unseen tasks.
What they offer
- Meaningful equity (U.S. only)
- 100% coverage of medical, dental, and vision insurance for employee and dependents
- Flexible PTO policy
- Paid parental leave
- Fertility and family-building stipend through Carrot (U.S. only)
- Company-facilitated 401(k)
Ideal candidate
A curious experimentalist who enjoys designing informative experiments and digging into failures. You care about open research and building environments that teach models reliable, transferable capabilities.
Requirements
- Ability to choose a useful research question, design informative experiments, and reason carefully about results
- Depth in reinforcement learning, model evaluation, agent systems, synthetic data, or experimental methodology
- Comfortable writing code to build environments, run experiments, and inspect failures in detail
Lab profile
About Baseten
Powers mission-critical AI inference to bring cutting-edge models into production.
What they build
- Mission-critical inference platform
- Flexible infrastructure for production models
- Developer tooling for AI deployment
Known for
- Applied AI research
- Flexible infrastructure
- Seamless developer tooling
Key facts
- Raised Series F
Posted · Last seen