Legion Health
Founding Engineer | AI-Native Ops Infrastructure (backed by Y Combinator, $3M+ A
Legion Health, San Francisco, California, United States, 94199
About Legion Health
Legion Health (YC S21) is building the
AI-native operations layer for psychiatric care . We run our own psychiatric practice and are rebuilding what happens
outside
the visit—scheduling, intake, documentation, billing, risk detection, and coordination. Not “doctor-in-a-box,” but the operational backend that mental health actually runs on. Our agent infrastructure already supports
2,000+ patients with one human support lead . The systems you build will land in real clinical workflows immediately. Role: Founding Engineer – AI-Native Ops Infrastructure (In-Person SF)
Hey—I’m Daniel, co-founder & CTO. I’m hiring a
Founding Engineer
to own core backend + agent systems end-to‑end. You’ll help design and build the infrastructure that coordinates human clinicians, support staff, and AI agents like a single, coherent system. Roles evolve quickly here—including mine. I’m looking for someone who wants to
grow into owning major parts of the system , not someone depending on me to stay in a narrow CTO role forever. What you’ll do
Own our event-driven backend
– Architect and scale our Node.js / TypeScript / Supabase (Postgres) / AWS stack. Design schemas, invariants, and workflows that encode how psychiatric care actually operates. Turn messy real‑world processes into clean state machines and event streams.
Build real LLM agents as coworkers
– Implement tool use, retries, memory, and safety rails. Design action schemas and evaluation loops so agents can run reliably in production. Work on orchestration, context management, and multi‑step workflows.
Shape human + AI ops UX
– Build internal tools used by both humans and agents. Make it trivial to see “what happened, why, and what should happen next” in any patient journey.
Define world-state & simulation
– Model the canonical state of a patient’s journey across time. Power alerting, routing, and decision‑making from that live simulation.
Own data, safety & compliance
– Engineer HIPAA‑compliant pipelines for transcripts, events, and EHR data. Ensure PHI access, agent actions, and human overrides are all auditable.
Drive architecture & strategy
– Work directly with me to debate tradeoffs, define new primitives, and decide what we build next.
You don’t need to be a pure backend engineer—we value
great product engineers who can learn fast , make strong simplifying decisions, and grow into owning backend/agent systems. You might be a fit if…
You’ve
owned real systems 0→1 or 1→N , not just tickets.
You think in
events, state, and invariants , not just CRUD endpoints.
You’re either already
LLM-fluent
or a strong systems/backend engineer who can get dangerous fast.
You care about velocity
and
correctness—moving quickly while keeping things understandable and robust.
You like small, high‑candor teams and direct feedback.
You want to see your work go live in production
weekly , not sit on a roadmap.
Nice to have (but not required)
Experience with Node.js / TypeScript, Postgres, or Supabase.
Experience with LLMs, agents, tool‑calling, or RAG.
Experience in healthcare, fintech, or other regulated / high‑stakes domains.
Experience in early‑stage startups or founding teams.
Our stack
Backend: Node.js, TypeScript, Supabase (Postgres), AWS (ECS, Lambda, S3)
Frontend: Next.js 15 (App Router), Tailwind, Vercel
AI: OpenAI, Anthropic, tool‑calling agents, embeddings + vector DBs, Langfuse‑style observability
Other: PHI security, audit trails, real‑time schedulers, transcript ingestion
Interview process
Intro call (20–30 min) with Daniel – background, what you’ve built, what you want.
Systems / portfolio deep dive (45–60 min) – walk through 1–2 systems you’ve shipped; architecture, tradeoffs, failure modes.
Practical work trial (1–2 hours async) – short, realistic backend/LLM‑systems exercise. No leetcode, no puzzles.
Final onsite (1–2 hours) – meet the team, pair on a real issue, and talk through how you’d own a domain. We aim to go from first conversation to offer in
7–10 days .
Compensation
Salary:
$130,000–$180,000
(depending on experience)
Equity:
0.2%–0.8%
meaningful early ownership
In‑person in San Francisco
#J-18808-Ljbffr
Legion Health (YC S21) is building the
AI-native operations layer for psychiatric care . We run our own psychiatric practice and are rebuilding what happens
outside
the visit—scheduling, intake, documentation, billing, risk detection, and coordination. Not “doctor-in-a-box,” but the operational backend that mental health actually runs on. Our agent infrastructure already supports
2,000+ patients with one human support lead . The systems you build will land in real clinical workflows immediately. Role: Founding Engineer – AI-Native Ops Infrastructure (In-Person SF)
Hey—I’m Daniel, co-founder & CTO. I’m hiring a
Founding Engineer
to own core backend + agent systems end-to‑end. You’ll help design and build the infrastructure that coordinates human clinicians, support staff, and AI agents like a single, coherent system. Roles evolve quickly here—including mine. I’m looking for someone who wants to
grow into owning major parts of the system , not someone depending on me to stay in a narrow CTO role forever. What you’ll do
Own our event-driven backend
– Architect and scale our Node.js / TypeScript / Supabase (Postgres) / AWS stack. Design schemas, invariants, and workflows that encode how psychiatric care actually operates. Turn messy real‑world processes into clean state machines and event streams.
Build real LLM agents as coworkers
– Implement tool use, retries, memory, and safety rails. Design action schemas and evaluation loops so agents can run reliably in production. Work on orchestration, context management, and multi‑step workflows.
Shape human + AI ops UX
– Build internal tools used by both humans and agents. Make it trivial to see “what happened, why, and what should happen next” in any patient journey.
Define world-state & simulation
– Model the canonical state of a patient’s journey across time. Power alerting, routing, and decision‑making from that live simulation.
Own data, safety & compliance
– Engineer HIPAA‑compliant pipelines for transcripts, events, and EHR data. Ensure PHI access, agent actions, and human overrides are all auditable.
Drive architecture & strategy
– Work directly with me to debate tradeoffs, define new primitives, and decide what we build next.
You don’t need to be a pure backend engineer—we value
great product engineers who can learn fast , make strong simplifying decisions, and grow into owning backend/agent systems. You might be a fit if…
You’ve
owned real systems 0→1 or 1→N , not just tickets.
You think in
events, state, and invariants , not just CRUD endpoints.
You’re either already
LLM-fluent
or a strong systems/backend engineer who can get dangerous fast.
You care about velocity
and
correctness—moving quickly while keeping things understandable and robust.
You like small, high‑candor teams and direct feedback.
You want to see your work go live in production
weekly , not sit on a roadmap.
Nice to have (but not required)
Experience with Node.js / TypeScript, Postgres, or Supabase.
Experience with LLMs, agents, tool‑calling, or RAG.
Experience in healthcare, fintech, or other regulated / high‑stakes domains.
Experience in early‑stage startups or founding teams.
Our stack
Backend: Node.js, TypeScript, Supabase (Postgres), AWS (ECS, Lambda, S3)
Frontend: Next.js 15 (App Router), Tailwind, Vercel
AI: OpenAI, Anthropic, tool‑calling agents, embeddings + vector DBs, Langfuse‑style observability
Other: PHI security, audit trails, real‑time schedulers, transcript ingestion
Interview process
Intro call (20–30 min) with Daniel – background, what you’ve built, what you want.
Systems / portfolio deep dive (45–60 min) – walk through 1–2 systems you’ve shipped; architecture, tradeoffs, failure modes.
Practical work trial (1–2 hours async) – short, realistic backend/LLM‑systems exercise. No leetcode, no puzzles.
Final onsite (1–2 hours) – meet the team, pair on a real issue, and talk through how you’d own a domain. We aim to go from first conversation to offer in
7–10 days .
Compensation
Salary:
$130,000–$180,000
(depending on experience)
Equity:
0.2%–0.8%
meaningful early ownership
In‑person in San Francisco
#J-18808-Ljbffr