Research Scientist
Job Summary
Join a well-funded, stealth AI start-up building frontier reasoning models for scientific discovery. The team tackles problems requiring models to generate, evaluate, and refine hypotheses across complex, multi-step scientific workflows.
About the role
The role involves developing reasoning models and post-training pipelines for frontier language and multimodal models, building evaluation frameworks and benchmarks for complex, multi-step reasoning, improving model performance through reinforcement learning, alignment, and scalable experimentation, and exploring reasoning across multimodal inputs where language and vision intersect to solve scientific problems. You will work closely with a small research team to rapidly test and deploy new ideas.
Responsibilities
- Developing reasoning models and post-training pipelines for frontier language and multimodal models.
- Building evaluation frameworks and benchmarks for complex, multi-step reasoning.
- Improving model performance through reinforcement learning, alignment, and scalable experimentation.
- Exploring reasoning across multimodal inputs, where language and vision intersect to solve scientific problems.
- Working closely with a small research team to rapidly test and deploy new ideas.
Requirements
- Strong experience in LLM post-training, RL for reasoning, reasoning datasets, evaluation, or alignment.
- Experience with multimodal or vision-language models (VLMs), especially where you've worked on reasoning.
- Exceptional researchers from pure language model backgrounds are also encouraged to apply.
Qualifications
- PhD graduate, Research Engineer, Applied Researcher, or experienced Research Scientist with hands-on ownership of reasoning systems.
Skills
- Frontier reasoning, post-training, reinforcement learning, alignment, scalable experimentation.
- Exploring reasoning across multimodal inputs, where language and vision intersect to solve scientific problems.
Benefits
- $250K - $400K Base (D.O.E.)
- Equity
- Very lucrative bonus/success structure
Pay
$250K - $400K Base (D.O.E.)
Schedule
Not specified
Location
San Francisco