Posted 1d ago

Baseten Posted 1d ago
Base Labs Research Scientist - RL Environments
Location
San Francisco
Hybrid
Contract
Permanent
Full-time
Salary
Not disclosed
Experience
Not specified
Job summary
Responsibilities
Models learn from the environments we give them. If a reward is easier to exploit than a task is to solve, a model can learn the shortcut. If a task measures the wrong capability, a higher score tells us little about progress.
- Identify capabilities and failure modes worth studying, informed by real model use. These may include software development, tool use, scientific reasoning, and following complex…
- Design task distributions, interactions, rewards, and verifiers together. Establish that tasks are solvable and that success depends on the intended capability.
- Build methods that scale environment creation without weakening the quality standard. Study how to generate diverse tasks, calibrate difficulty, and detect defects before they…
- Run RL experiments to measure learning and transfer. Compare curricula, task mixtures, and reward designs; investigate failed runs and unexpected behavior; test whether…
- Develop evaluation methods that distinguish capability differences from sampling noise, grader errors, or artifacts of the agent’s tools and execution setup.
Tech stack
Read the full job posting
This summary is written by Tokn from the original posting. Only the posting published by Baseten is authoritative. Request a removal
Similar jobs
All Research jobs in San Francisco →Posted 1d ago
Posted 1d ago

