Research, Post-Training
$350k - $475k • San Francisco • FullTime
Posted 2mo ago
Job Location
San Francisco
Tech Stack
Remote Work Policy
On-site
Employment Type
FullTime
Categories
AI Research Engineer
About the job
The role
of post-training researchers sits at the core of our roadmap, serving as the critical bridge between raw model intelligence and a system that is actually useful, safe, and collaborative for humans. This position blends fundamental research and practical engineering, requiring proficiency in writing high-performance code and reading technical reports. It's an excellent fit for individuals who enjoy both deep theoretical exploration and hands-on experimentation, and who wish to shape the foundations of how AI learns. This is an evergreen role, kept open to express interest in this research area, with applications continuously reviewed for emerging opportunities.
Responsibilities
- Develop and tune post-training recipes, including datasets, training stages, and hyperparameters, measuring the impact of choices on various metrics.
- Iterate on evaluation methodologies, defining, optimizing, and refining evaluations to ensure they meaningfully capture desired outcomes.
- Debug and understand training configurations, ensuring functionality and developing deeper insights into observed results.
- Scale existing methodologies and explore new ones, measuring performance metric scaling with dataset size and investigating novel training datasets.
- Publish and present research, sharing code, datasets, and insights to advance the broader AI community.
Requirements
- Proficiency in Python and at least one deep learning framework (e.g., PyTorch, TensorFlow, JAX).
- Comfort with debugging distributed training and writing scalable code.
- Bachelor’s degree or equivalent experience in Computer Science, Machine Learning, Physics, Mathematics, or a related discipline with strong theoretical and empirical grounding.
- Clarity in communication and the ability to explain complex technical concepts in writing.
- Strong grasp of probability, statistics, and ML fundamentals, with the ability to distinguish real effects from noise and bugs.
- Prior experience with RLHF, RLAIF, preference modeling, or reward learning for large models.
- Experience managing or analyzing human data collection campaigns or large-scale annotation workflows.
- Research or engineering contributions in alignment, data-centric AI, or human-AI collaboration.
- PhD in Computer Science, Machine Learning, Physics, Mathematics, or a related discipline with strong theoretical and empirical grounding; or equivalent industry research experience.
Benefits
- Generous health, dental, and vision benefits
- Unlimited PTO
- Paid parental leave
- Relocation support