Research Engineer - Environments, Data and Post-Training

📋 Description

• Work on post-training and RLVR pipelines; assess data, rewards, and training impact.
• Design and run reward-shaping experiments (GRPO, DAPO) to improve tool-use.
• Quantify data usability, quality, and performance on benchmarks.
• Build data generation and augmentation pipelines at scale.
• Create rubrics, evaluators, and scoring frameworks for training.
• Build and operate LLM evaluation systems and metrics at scale.

🎯 Requirements

• Strong applied research in post-training and model evaluation.
• Strong coding skills with ML models.
• Understanding of data structures, algorithms, and backend systems.
• Familiarity with APIs, SQL/NoSQL, and cloud platforms.
• Ability to reason about model behavior and data quality.
• Willingness to work in person in SF five days a week.

🎁 Benefits

• Bi-annual performance bonus structure
• Generous equity grant vested over 4 years
• Up to $15k Relocation bonus
• $10K housing bonus (if you live within 0.5 miles of our office)
• $1.5K monthly stipend for meals
• Free Equinox membership