Research Scientist, Post-Training

About the Role

Join a post-training research team at an applied AI research company focused on training data for foundation models. You will design controlled experiments to determine how datasets affect model behavior, then turn the findings into practical improvements to data and evaluation.

What You'll Do

• Run controlled supervised fine-tuning (SFT) and reinforcement learning experiments to measure dataset impact on model performance.

• Build evaluation infrastructure and benchmarks that support reproducible comparisons across models, capabilities, and domains.

• Help develop public evaluations and new data types for frontier models.

• Publish external-facing research, blog posts, and technical reports.

• Collaborate with internal teams to improve data quality based on experimental findings.

What We're Looking For

• Zero to four years of experience building or delivering work in LLM training, post-training, or model evaluation.

• Experience at a frontier AI lab.

• Strong familiarity with LLM training and evaluation methods, including the ability to independently design, implement, and analyze controlled experiments.

• Ability to build or modify experimental infrastructure, such as evaluation harnesses, training pipelines, or benchmarks.

• Comfort moving quickly, interpreting messy results, and extracting actionable insights.

• Experience working across domains such as finance, software engineering, and policy.

• Meaningful research or hands-on work in model evaluation, post-training, or data curation is valuable.

Compensation & Benefits

Base salary: $150,000 to $250,000 annually. Visa sponsorship is available.

Location

On-site in San Francisco, California, United States.