Founding Engineer — AI-Native Mental Health Startup

Founding Engineer — AI-Native Mental Health Startup

Location: San Francisco, CA (Onsite, in-person at SF HQ — no remote)

Compensation: $130,000 – $250,000 base + 0.20%–0.80% equity

Visa Sponsorship: None available

Relocation: No relocation assistance provided

Employment Type: Full-Time

Headcount: 2 open seats

About the Company

A YC-backed startup building AI-native mental health care. The team uses modern language models and data tooling to expand access to high-quality psychiatric care and to streamline clinical operations, integrating AI across the patient and provider experience.

About the Role

As a Founding Engineer, you'll own core product and agent systems end-to-end — the layer that coordinates patients, clinicians, and AI agents as one coherent system. This is not "just infra": it's the product heart of an autonomous care system, including the workflows, agent behaviors, guardrails, integrations, the UX that makes it usable, and the reliability that makes it trusted. Roles evolve quickly here, and top performers on the founding team are expected to grow into running major parts of the system.

Tech 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 databases, observability tooling
• Other: PHI security, audit trails, real-time schedulers, transcript ingestion

What You'll Own

• Architect and scale an event-driven backend on Node.js / TypeScript / Supabase (Postgres) / AWS — designing schemas, invariants, and workflows that encode how care actually operates, turning messy real-world processes into clean state machines and event streams
• Build real LLM agents as coworkers — tool use, retries, memory, safety rails, action schemas, and evaluation loops so agents run reliably in production
• Build internal ops tooling used by both humans and agents — making it easy to see what happened, why, and what should happen next in any patient journey
• Model the canonical world-state of a patient's journey to power alerting, routing, and decisions
• Engineer HIPAA-compliant pipelines for transcripts, events, and EHR data, with auditable PHI access and overrides
• Partner directly with the founder on architecture, tradeoffs, and what to build next

Requirements

• 3–5 years shipping production products using TypeScript, Next.js, and Postgres (Supabase and Vercel a strong plus)
• Proven backend/systems depth: relational data modeling, stateful workflows, valid transitions, and invariants that hold by construction (e.g. no double-booked provider slots, no comms triggered by cancelled appointments, agents that can't spam or duplicate)
• Able to independently build both human-facing surfaces (ops dashboards, admin tools) and background orchestration (scheduled jobs, workflows, agent runs)
• Heavy, habitual user of AI-native dev tools (Cursor, Claude Code, Codex, etc.) with real opinions on how they accelerate shipping
• Excited about early-stage execution and shipping to production weekly; wants to operate as a hands-on IC
• Based in San Francisco or willing to relocate (onsite, in-person)
• Authorized to work in the U.S. — no sponsorship available

Nice to Have

• Experience building and monitoring production LLM features (tool-calling, RAG, agents)
• Previous early-stage startup or founding-engineer experience
• Experience in regulated / high-stakes domains (healthcare, HIPAA, fintech)
• Feature ownership at meaningful scale (10k–100k users), performance work on data-heavy dashboards, and pragmatic CI/testing that increases velocity

Target Backgrounds

Strong signals include early-stage product engineers shipping TypeScript/Next.js/Postgres with real users; hands-on technical founders or early engineers on small teams; engineers who've built ops dashboards or control planes for stateful systems; and engineers who've shipped LLM product features in JS/TS stacks.

This Role Is NOT For

• Remote-only candidates — this role is fully in-person in San Francisco
• Frontend / UI-only engineers without backend or systems depth
• Managers or executives looking to step back from hands-on coding
• Candidates without recent production shipping in Next.js + TypeScript + Postgres

Interview Process

1. Systems / portfolio deep dive (45 min) — walk through 1–2 systems you've shipped: architecture, tradeoffs, failure modes
2. Practical work trial (1.5 hrs) — short, realistic backend/LLM-systems exercise (no LeetCode, no puzzles)
3. Final onsite (1.5 hrs) — meet the team, pair on a real issue, and talk through owning a domain

Estimated time-to-hire: 7–10 days. Start date: ASAP.

Application Questions

• Share an example of shipping in high ambiguity and how you decided what to build first.
• Describe any experience building or integrating LLM / AI-powered features into production.
• Why are you excited about this role and company?

Benefits

• Meaningful early equity (0.20%–0.80%)
• Medical, dental, and vision insurance
• 401(k)
• Flexible, unlimited vacation policy
• In-person retreats and meal stipends

Logistics

• Role is fully onsite in San Francisco — please only apply if you can commit to this
• No visa sponsorship available

Shortlisted candidates will be contacted by David Joseph & Co. , the recruiting partner managing this search on behalf of the client.