About the RoleWe're hiring a materials scientist to bridge our computational and experimental databases with the LLM agents that need to navigate them. This is a hybrid research and infrastructure role: you'll spend roughly half your time restructuring our materials databases so they're legible to agentic systems, and the other half working directly with our lab scientists and computational team on active research problems.
The database work requires real domain depth, not just data engineering skill. For example, you need to know what metadata actually matters for a given characterization technique. The research work keeps you grounded in the problems we're actually using LLMs to solve, so the schemas you build serve real research rather than an abstraction of it.
You'll be as much a materials scientist doing research as you are the person making our agentic harness actually work.
What You'll Do- Restructure and re-architect materials databases (lab experiments, characterization data, computations) so they're usable by agentic systems, drawing on domain expertise about how to represent the data and what metadata matters
- Work directly with lab scientists and the computational team on active research problems, staying close to the actual bottlenecks LLM agents are meant to solve
- Design data structures around how LLM agents actually reason and fail, not just around human readability
- Build research software for lab environments, translating scientific requirements into working tools
- Move fluidly between research contribution and infrastructure ownership, splitting time roughly evenly between the two
Mechanics- Minimum experience: 4+ years
- Minimum education: PhD in Materials Science, Chemistry, or a related field, or equivalent industry experience
- Location: Menlo Park, CA or Montreal, Canada. (Soon: San Francisco, too)
- Compensation: $250,000-350,000 + equity
- Visa sponsorship: Yes, we sponsor visas.
