Python · TensorFlow · PyTorch · Keras · Scikit-learn
ABOUT THE ROLE
Join a post-training research team at a Series A AI training data company. You will design controlled experiments to determine how training data affects model capabilities, generalization, and alignment, then turn the findings into practical recommendations.
WHAT YOU'LL DO
- Run controlled supervised fine-tuning (SFT) and reinforcement learning (RL) experiments to measure dataset impact on model performance.
- Help develop public evaluations and new data types that advance model training and assessment.
- Build shared evaluation infrastructure and benchmarks to make results reproducible across models, capabilities, and domains.
- Publish external research, blog posts, and technical reports.
- Collaborate with internal teams to improve data quality based on experimental results.
WHAT WE'RE LOOKING FOR
- Zero to four 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 hands-on SFT and RL post-training.
- Ability to design lightweight experiments and draw actionable insights from messy results.
- Experience working across domains such as finance, software engineering, and policy.
- Software engineering skills and experience independently building or modifying evaluation harnesses, training pipelines, benchmarks, or related experimental infrastructu