Research Scientist - Post Training

About the role

We are a small, early-stage team (post-Series A) dedicated to building training data and evaluation infrastructure for AI labs. Our mission is to design high-signal datasets and conduct rigorous evaluations that push the boundaries of model learning and improvement.

What You'll Do

• Run controlled Self-Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) experiments to measure the impact of our datasets on model performance.
• Quantify the lift across various capabilities such as reasoning, tool use, long-horizon tasks, and domain-specific workflows.
• Share findings directly with partner labs to deepen relationships and drive sales.
• Collaborate with internal Specialized Product Leads (SPLs) to iterate on data quality based on your results.
• Work closely with the other Research Scientists on this team to build shared experimental infrastructure and benchmarks.

What We're Looking For

• Strong familiarity with LLM training and evaluation methodologies, including SFT and RL post-training.
• Genuine obsession with how data structure, selection, and quality drive model behavior.
• Ability to design lightweight experiments, move fast, and extract actionable insights from messy results.
• Comfort working across domains including finance, software engineering, policy, and more.
• A bias toward building over theorizing.

Must-Have Requirements

• Strong familiarity with LLM training and evaluation methodologies, including SFT and RL post-training.
• Genuine obsession with how data structure, selection, and quality drive model behavior.
• Ability to design lightweight experiments, move fast, and extract actionable insights from messy results.
• Comfort working across domains including finance, software engineering, policy, and more.
• An undergraduate or master's research background; pre-PhD candidates preferred.

Nice-to-Have Requirements

• Prior work or internship at an RL environment company, AI safety organization, or benchmarking organization (such as METR, Artificial Analysis, etc.).
• Experience running controlled training experiments end-to-end.
• Published research on model evaluation, post-training, or data curation.
• Strong Software Engineering (SWE) chops alongside research instincts.

Compensation

$250K–$450K total compensation + equity

Requirements

• Run controlled SFT and RL experiments to measure dataset impact on model performance.
• Quantify lift across capabilities including reasoning, tool use, long-horizon tasks, and domain-specific workflows.
• Communicate findings with partner labs to drive sales.
• Work with internal SPLs to iterate on data quality based on experimental results.
• Design lightweight experiments and extract actionable insights from messy results.
• Work across multiple domains including finance, software engineering, and policy.