Founding Engineer (AI)

TL;DR

Founding Engineer (AI/TypeScript): Building an autonomous mental healthcare system with an accent on AI agent orchestration and event-driven backend systems. Focus on developing LLM-powered teammates, designing HIPAA-compliant data pipelines, and scaling a high-reliability clinical operator.

Location: In-person at San Francisco HQ

Company

hirify.global is building autonomous mental healthcare AI that takes responsibility across the full care loop to make psychiatric care fast, affordable, and excellent at scale.

What you will do

• Architect and scale an event-driven backend using Node.js, TypeScript, Supabase, and AWS.
• Implement real LLM agents with tool use, memory, and safety rails for production workflows.
• Build internal human+AI operations UX to monitor and manage patient journeys.
• Model the canonical state of patient journeys to power alerting, routing, and decision-making.
• Engineer HIPAA-compliant pipelines for transcripts, events, and EHR data.
• Collaborate directly with the CTO to define technical strategy and system primitives.

Requirements

• Proven experience owning systems from 0→1 or 1→N.
• Strong proficiency in thinking in events, state, and invariants.
• LLM fluency or deep systems/backend engineering expertise with the ability to learn AI quickly.
• Ability to work in-person in San Francisco.
• Commitment to high velocity and correctness in a high-candor startup environment.

Nice to have

• Experience with Node.js, TypeScript, Postgres, or Supabase.
• Knowledge of LLMs, agents, tool-calling, or RAG.
• Experience in healthcare, fintech, or other high-stakes regulated domains.
• Previous experience in early-stage startups or founding teams.

Culture & Benefits

• Meaningful early ownership with 0.2%–0.8% equity.
• Comprehensive medical, dental, and vision insurance.
• Flexible, unlimited vacation policy.
• Additional perks including meal stipends and in-person retreats.
• US Visa Sponsorship is available.

Hiring process

• Systems/portfolio deep dive (45 min) to discuss shipped architecture and tradeoffs.
• Practical work trial (1.5 hours) focused on realistic backend/LLM systems exercises.
• Final onsite (1.5 hours) including team meetings and pair programming on a real issue.