Senior Full Stack Engineer (Back-End), AI Startup, San Francisco (On-Site)

WhyHireWrong?•American Fork, UT

14h•$180,000 - $240,000•Onsite

About The Position

This is an urgent hire for a backend-leaning full-stack engineer to work directly with the CTO. The role involves building and scaling core infrastructure for a $30M seed-stage AI platform. The position requires 5 days a week on-site work in San Francisco and is a full-time role.

Requirements

5+ years of production backend engineering experience, including on-call.
Fluent in TypeScript, with a backend-primary focus.
Full stack experience across the production stack: TypeScript, Cloudflare Workers, Durable Objects, Hono, Drizzle ORM, Postgres, Zod, SST, Vercel AI SDK, Docker, React, Vite.
Shipped real-time systems to external users in production (WebSockets, SSE, event streaming, or message queues), with the ability to describe specific scaling bottlenecks.
Designed distributed systems and made concrete consistency tradeoffs, with the ability to explain choices and trade-offs.
Shipped infrastructure that real external users depended on (not internal tooling), with the ability to name the system, user load, and operational responsibility.
Experience with LLM agent loops, model routing layers, or tool-use architectures (does not require ML depth, but must have familiarity with agent interaction patterns).
Based in San Francisco Bay Area or willing to relocate before the start date for 5-days-a-week on-site work at the Presidio.
US work authorization required. O-1 or J-1 sponsorship considered for exceptional candidates only. H-1B is not offered.

Nice To Haves

Production experience with Cloudflare Workers, Durable Objects, or serverless edge compute.
Experience building agent runtimes, model routing layers, or tool-use architectures with LLMs in production.
Ex-founder or ex-CTO experience.
Experience as an early engineer at an AI-native startup.
Actively building or experimenting with AI outside of work.
Has tried the product before interviewing.
Open to a paid in-person work trial of a few days up to two weeks.

Responsibilities

Build core backend infrastructure including agent runtimes, SSE streaming pipelines, task queues, and multi-model LLM provider routing, shipped to real external users.
Develop an edge compute layer using Cloudflare Workers and Durable Objects with Fly.io blue-green and canary deployments.
Build real-time systems at scale, including WebSockets, SSE, event streaming, and message queues under production load.
Design distributed system architecture, considering consistency tradeoffs, failure modes, and operational runbooks for a 15-person team.
Participate in an on-call rotation, respond to incidents, and own resolution end to end.