Agent Engineer for Scientific AI (Equity & Unlimited PTO)

Phylo; South San Francisco (CA); On-site; USD 200,000 - 300,000; Full time

Benefits offered by this job

Competitive salary

Equity

Medical, dental & vision coverage

401(k) plan

Unlimited PTO

Lunch & snacks in office

Team offsites

Job summary

Phylo is an applied research lab accelerating discovery through AI agents. We seek an engineer to build and evaluate systems that make agents capable, reliable, and better. You will own production harnesses, incorporate cutting-edge research, and drive experiments to measure improvements on scientific tasks.

The role emphasizes strong software engineering, ML background, and a hands-on approach to productionizing agent capabilities within a research-driven biomedical context.

Qualifications

• Strong software engineering experience building production backend systems.
• Research or production experience in machine learning or a quantitative discipline.
• Familiarity with LLM APIs, tool calling, agent runtimes, or workflow orchestration.
• Strong quantitative judgment to determine real, reproducible improvements.
• Ability to move between research questions, data analysis, system design, and production implementation.

Responsibilities

• Advance the agent harness by bringing latest research into production and experimenting with multi-agent coordination, model routing, memory, planning, and tool use.
• Build rigorous evaluations measuring agent quality, reliability, latency, and cost on scientific tasks.
• Monitor agent quality in production, troubleshoot failures quickly in high-ambiguity situations, translate findings into engineering improvements.
• Collaborate on reliable infrastructure for long-running sessions, sandboxed execution, background work, and subagents.
• Partner with scientists and engineers to productionize new agent capabilities.

Skills

Production backend systems

Quantitative mindset

ML/AI knowledge

LLM APIs familiarity

Ownership & communication

Job description

Phylo is an applied research lab accelerating discovery through AI agents. We seek an engineer to build and evaluate systems that make agents capable, reliable, and better. You will own production harnesses, incorporate cutting-edge research, and drive experiments to measure improvements on scientific tasks.

The role emphasizes strong software engineering, ML background, and a hands-on approach to productionizing agent capabilities within a research-driven biomedical context.