Member of Technical Staff - Agent Engineer
Phylo, Inc., South San Francisco
The role
We’re looking for an engineer with research or production experience in AI agents to build and evaluate systems that make our agents capable, reliable, and measurably better.
The model is only one part of an agent; the harness shapes how it plans, uses tools, manages context, coordinates work, and recovers from failure. You will own these systems in production and build evaluations to measure whether changes improve performance. The work includes bringing the latest advances and original ideas into production. The ideal candidate combines strong engineering execution with a quantitative mindset and an interest in AI agents for scientific discovery.
What you will do
- Advance the agent harness by bringing the latest research and open-source developments into production and experimenting with new approaches to multi-agent coordination, model routing, memory, planning, and tool use.
- Build rigorous evaluations that measure agent quality, reliability, latency, and cost on representative scientific tasks.