Phylo is an applied research lab building agentic intelligence to accelerate discovery for every biomedical scientist. They are seeking an engineer with research or production experience in AI agents to build and evaluate systems that enhance agent capabilities and reliability. The role involves advancing agent harnesses, building rigorous evaluations, and collaborating with scientists and engineers to productionize new agent capabilities.
Responsibilities:
- 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
- Monitor agent quality in production, troubleshoot failures quickly in high-ambiguity situations, and translate findings into engineering improvements
- Collaborate on reliable infrastructure for long-running sessions, safe sandboxed execution, background work, and subagents
- Partner with scientists and engineers to evaluate and productionize new agent capabilities