Senior Full Stack Engineer (Back-End) – AI Platform

About the role

Join a fast‑growing AI startup to build the core infrastructure of its platform alongside the CTO. You will ship real‑time distributed systems, agent runtimes, and production features that customers rely on.

Key responsibilities

• Design and implement core backend infrastructure such as agent runtimes, SSE streaming pipelines, task queues, and multi‑model LLM routing.
• Develop an edge compute layer using Cloudflare Workers, Durable Objects, and Fly.io blue‑green/canary deployments.
• Build and operate real‑time systems at scale, including WebSockets, SSE, event streaming, and message queues.
• Define distributed system architecture, consistency trade‑offs, failure modes, and operational runbooks for a small, fast‑moving team.
• Participate in on‑call rotation, respond to incidents, and own end‑to‑end resolution.

Required profile

• 5+ years of production backend engineering experience, including on‑call responsibilities.
• Deep fluency with TypeScript and a backend‑first mindset.
• Experience shipping real‑time systems to external users and designing distributed systems with concrete consistency decisions.
• Hands‑on work with LLM agent loops, model routing layers, or tool‑use architectures.
• Based in the San Francisco Bay Area or willing to relocate for a full‑time onsite role.
• US work authorization required; O‑1 or J‑1 sponsorship considered for exceptional candidates.

Required skills

• TypeScript
• Cloudflare Workers
• Durable Objects
• Hono
• Drizzle ORM
• PostgreSQL
• Zod
• SST
• Vercel AI SDK
• Docker
• React
• Vite
• WebSockets
• Server‑Sent Events (SSE)
• Event streaming
• Message queues
• Distributed systems design
• LLM agent loops
• Model routing
• Tool‑use architectures

What we offer

• Yearly salary ranging from $180,000 to $240,000.
• Paid in‑person work trial of up to two weeks with accommodation and flights covered for relocating candidates.
• Full‑time onsite work (5 days a week) at the Presidio office.