Requirements
- 0 to 4 years of experience in research or machine learning roles building or delivering LLM training, evaluation, or post-training systems.
- Experience at a frontier AI lab and a track record of independently designing, implementing, and analyzing controlled experiments.
- Strong familiarity with LLM training and evaluation methodologies, including end-to-end post-training experiments.
- Ability to design lightweight experiments and draw actionable conclusions from noisy or incomplete results.
- Experience across domains such as finance, software engineering, and policy.
- Software engineering skills to independently build or modify evaluation harnesses, training pipelines, benchmarks, or other experimental infrastructure.
Benefits
- Visa sponsorship
Skills
Full job description
Description
About the Role
Join a post-training research team at a Series A AI research and training data company. You will run rigorous experiments to establish how training data influences model capabilities, generalization, and alignment, and turn the results into practical guidance.
What You'll Do
Design and run controlled supervised fine-tuning (SFT) and reinforcement learning (RL) experiments to measure the impact of datasets on model performance.
Help develop public evaluations, benchmarks, and new data types that advance model research.
Build shared evaluation infrastructure so results can be reproduced across models, capabilities, and domains.
Translate experimental findings into recommendations for data quality, selection, and production.
Publish external-facing research, blog posts, and technical reports, and collaborate with partner research teams.
Location
On-site in San Francisco, United States.
Requirements
What We're Looking For
0 to 4 years of experience in research or machine learning roles building or delivering LLM training, evaluation, or post-training systems.
Experience at a frontier AI lab and a track record of independently designing, implementing, and analyzing controlled experiments.
Strong familiarity with LLM training and evaluation methodologies, including end-to-end post-training experiments.
Ability to design lightweight experiments and draw actionable conclusions from noisy or incomplete results.
Experience across domains such as finance, software engineering, and policy.
Software engineering skills to independently build or modify evaluation harnesses, training pipelines, benchmarks, or other experimental infrastructure.
Meaningful research or publications related to model evaluation, post-training, or data curation.
Benefits
Compensation & Benefits
Base salary: $150,000 to $250,000 annually. Visa sponsorship is available.
Opens True Talent Solutions Partners’s own application page in a new tab.