OverviewAs a SWE (Environments), you will design the simulations, data, and evaluations that directly influence how frontier models learn. You'll work hands-on with research teams at top AI labs, experimenting with environment design, piloting novel data creation strategies, diagnosing model failure modes, and developing the metrics that determine whether a model is actually improving. You'll go from hypothesis to live experiment quickly, and your output will feed directly into model training runs at scale. Day to day, you will design environments, tasks, and data that expose meaningful failure modes across domains like finance, code, and enterprise workflows. You will build and refine reward signals for various RL pipelines. You will develop quantitative frameworks for measuring dataset quality, diversity, and downstream impact on alignment and capability. You will partner with lab research teams to translate their training objectives into concrete data and evaluation specifications.
Responsibilities- Construct simulated worlds and explore data shapes that expose meaningful model failure modes across domains like finance, code, and enterprise workflows
- Build and refine evaluation rubrics and reward signals for RLHF and RLVR training pipelines
- Analyze agent-produced trajectories and run experiments to improve different model capabilities
- Develop quantitative frameworks for measuring dataset quality, diversity, and downstream impact on model alignment and capability
- Create and manage both real world & synthetic data pipelines
Partner with lab research teams to translate their training objectives into concrete data and evaluation specifications - Partner with in-house researchers to run post-training experiments and scale training infrastructure
Required Qualifications- Ability to design lightweight experiments, move fast, and extract actionable insights from messy results
- Experience with using Docker, or similar containerization tools, to design and monitor systems at scale
- Strong familiarity with common reinforcement learning algorithms and methods, especially with respect to post-training LLMs
Preferred Qualifications- Major plus if they've worked for/interned for any RL environment companies in the past or any AI safety or benchmarking orgs like METR, Artificial Analysis, etc.
- Former founders and early engineers at early stage startups are a plus. We want people who can demonstrate they work hard, learn fast, and care deeply about getting the details right.
Company Benefits (For Eligible Employees):- Health Insurance: Medical, Vision, Dental
- 401(k) with Employer Match
- Daily Meals: Daily UberEats Stipend
- Monthly Wellness Stipend
- Commute Covered
