Member of Technical Staff, Agentic Systems

GenMD; Palo Alto (CA); On-site; USD 180,000 - 250,000; Full time

Benefits offered by this job

Equity

Job summary

GenMD, a Stanford spin-off, is hiring to design and ship agent infrastructure for the Healthcare Datahub. You will own the systems that run AI researchers' assistants, focusing on orchestration, tool use, data catalogs, retries, and human-in-the-loop review.

You will collaborate with founders, researchers and partners to decide agent tasks, implement secure production services on cloud data infrastructure (GCP/BigQuery), and optimize prompts, tools, guardrails, latency and cost.

Qualifications

• 3+ years building production backend systems.
• Hands-on experience shipping LLM applications or agents.
• Experience with cloud data infrastructure (GCP/BigQuery) and building secure, well-tested services.
• Own systems end to end and move quickly without lowering the bar.

Responsibilities

• Build and own agent infrastructure: orchestration, tool calling, retrieval over data catalogs and dictionaries, retries and fallbacks, and human-in-the-loop review.
• Ship agents into production and keep improving them against real usage: prompts, tools, guardrails, and cost and latency trade-offs.
• Build evaluation for agents: offline evals, online metrics and regression detection.
• Design the services, data models and APIs that keep agent actions auditable, permissioned and safe around sensitive healthcare data.
• Work directly with the founders, researchers and partners to decide what agents should do and where a human stays in the loop.

Skills

Python

TypeScript

LLM Agents

Cloud Data Infra

Tools

GCP

BigQuery

Job description

About GenMD

GenMD is a Stanford spin-off building AI and data infrastructure for healthcare. We grew out of years of work inside Stanford Medicine, alongside world-class researchers and clinicians, and we now work with health systems and data partners on large longitudinal datasets: claims, health records, imaging and clinical notes. We make that data usable for researchers and frontier AI, while patient privacy stays protected.

We're just coming out of stealth, already revenue-generating and well funded. We're intentionally small, move fast, and are focused on building something fundamental. Our CEO is a former Associate Director of AI at Stanford Medicine. See how we work: https://genmd.ai/careers

About the role

A growing share of GenMD's product runs on agents, starting with Mira, our AI research assistant on Healthcare Datahub. Mira helps researchers find the right dataset, explore cohorts and write analysis code. You'll design and ship the systems those agents run on, and own them in production against real researchers and real data.

What you'll do

• Build and own agent infrastructure: orchestration, tool calling, retrieval over data catalogs and dictionaries, retries and fallbacks, and human-in-the-loop review.

• Ship agents into production and keep improving them against real usage: prompts, tools, guardrails, and cost and latency trade-offs.

• Build evaluation for agents: offline evals, online metrics and regression detection that tell us whether an agent is actually working.

• Design the services, data models and APIs that keep agent actions auditable, permissioned and safe around sensitive healthcare data.

• Work directly with the founders, researchers and partners to decide what agents should do and where a human stays in the loop.

What we're looking for

• 3+ years building production backend systems; strong in Python or TypeScript.

• Hands-on experience shipping LLM applications or agents (tool use, structured outputs, evals).

• Experience with cloud data infrastructure (GCP/BigQuery preferred) and building secure, well-tested services.

• You own systems end to end and move quickly without lowering the bar.

Nice to have

• Experience with healthcare or other regulated data, data governance or access control.

• Experience building code-generating or data-analysis agents.

Compensation

$180,000 - $250,000 per year, plus equity. Final offer depends on experience.