Research Lead Training
Goodfire is a San Francisco AI interpretability research company building Silico, an agent and infrastructure for understanding, debugging, monitoring, and controlling AI models.
Funding history
About Goodfire
Goodfire is a public benefit corporation and AI interpretability research lab. Its current product, Silico, turns research questions into inspectable experiments and reports, supporting model analysis, debugging, guardrails, and interpretability research.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will lead model-training research and post-training work, set technical direction, define research agendas for intentional design and alignment, manage and mentor researchers, partner with scientific leadership, and build systems that deliver high-quality training outcomes.
Requirements
- Experience leading post-training, model training, or related efforts in a frontier AI environment
- Track record of owning ambitious technical programs combining research depth and execution
- Experience managing teams in fast-moving, high-expectation environments
- Judgment balancing long-term research with near-term product or model delivery
- Interest in intentional design, alignment, and interpretability-informed training
- Ability to work with senior scientific leadership and independently set direction
Responsibilities
- Lead the training organization and manage a high-performing team
- Set direction for model training
- Drive execution on post-training and model-improvement work
- Define and lead research in intentional design, interpretability-informed training, and alignment
- Partner with the Chief Scientist to shape priorities and translate strategy into execution
- Hire, mentor, and build the research team
Benefits
- Equity
- Competitive benefits
- One company-wide remote week per month