SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 250,000 - 350,000 / annual
Periodic Labs is an AI and physical sciences company building state-of-the-art models to accelerate breakthroughs in materials, energy, and related domains. The company is backed by world-class investors and operates at a rapid pace.
You will serve as a bridge between computational and experimental materials databases and LLM agents that need to navigate them. This is a hybrid research and infrastructure role, split roughly evenly between two major responsibilities:
1. Database Architecture & Restructuring: You'll re-architect materials databases (lab experiments, characterization data, computational results) to be legible and usable by agentic systems. This requires genuine domain expertise in materials science—not just data engineering skill. You need to understand what metadata actually matters for different characterization techniques, how to represent complex scientific data in ways that LLM agents can reason about, and how to design schemas that serve real research problems rather than abstract requirements.
2. Active Research Contribution: You'll work directly with lab scientists and the computational team on active research problems, staying close to the actual bottlenecks that LLM agents are meant to solve. This keeps your infrastructure work grounded in real scientific needs and ensures the tools you build actually address the problems researchers face.
Key responsibilities include:
- Restructuring and re-architecting materials databases so they're usable by agentic systems, drawing on domain expertise about data representation and metadata requirements
- Working directly with lab scientists and computational teams on active research problems
- Designing data structures around how LLM agents actually reason and fail, not just around human readability
- Building research software for lab environments, translating scientific requirements into working tools
- Moving fluidly between research contribution and infrastructure ownership
You'll be as much a materials scientist doing research as you are the person making the agentic infrastructure work. The role requires someone who can operate comfortably in both domains and understand the deep connections between them.
