Senior Full Stack Engineer (Back-End)_TT

We're looking for a Senior Full Stack Engineer with a strong backend focus to build and scale the core infrastructure of a fast-growing AI platform. You'll work directly with the CTO on backend systems, agent runtimes, and real-time infrastructure as the company brings on its first paying users. The work centers on TypeScript at the edge: Cloudflare Workers, Durable Objects, and Postgres, with SSE streaming, task queues, and routing across multiple LLM providers. You'll be comfortable across the stack, but your instinct is to go deeper on the backend and take ownership of reliability and operational excellence. The team is small, direct, and high-energy, and engineers are trusted to own big problems end-to-end. It's a great fit for a senior engineer with startup DNA who has shipped production infrastructure that real users depend on.

Details:
Schedule: Full time
Location: San Francisco, United States (Onsite, 5 days a week; relocation before start is possible)
Start: ASAP
Duration: Long-term
English: Fluent
Type of collaboration: Internal Employment

About the project: The company is a well-funded, seed-stage AI startup that has raised $30M to build a hybrid AI and software platform. The product acts as a shared brain for user context, bringing together information and actions so AI agents can do useful work for people. The team is about 15 people and growing, and many of them are former founders or CTOs. It is now onboarding its first paying users, so scaling the backend reliably is a top priority. The architecture combines Cloudflare Workers and Fly.io, with modern practices like blue-green rollouts and canary releases. This is a chance to shape the core infrastructure of an ambitious AI product at a very early stage.

You have:

• 5+ years of experience building and operating backend systems in production, including on-call responsibility
• Fluent TypeScript and comfort across the stack, with a clear preference for going deep on the backend
• Experience building real-time systems in production, such as WebSockets, SSE, event streaming, or message queues
• Strong distributed systems intuition, including a solid understanding of consistency tradeoffs
• Infrastructure you've shipped to real external users, not only internal tooling
• A working understanding of LLM agent loops and model interaction patterns (ML engineering depth is not required)
• Based in the San Francisco Bay Area or willing to relocate before starting; US work authorization (O-1 or J-1 sponsorship possible for exceptional candidates)
• A direct, proactive communication style suited to a small, in-person team
• Openness to a paid in-person work trial on a real project, from a few days to two weeks
• Nice to have: experience with Cloudflare Workers, Durable Objects, Fly.io, or other edge/serverless compute
• Nice to have: experience building agent systems, model routing layers, or LLM tool-use architectures
• Nice to have: background as a founder, CTO, or early engineer, ideally at an AI or agentic company
• Nice to have: hands-on AI side projects or active experimentation with AI tools
• Familiarity with parts of the stack is a plus: Hono, Drizzle ORM, Postgres, Zod, SST, Vercel AI SDK, Docker, React, Vite

What to do:

• Work directly with the CTO to design, build, and scale the core backend infrastructure
• Build and operate agent runtimes, including SSE streaming, task queues, and multi-model LLM provider routing
• Design distributed systems on Cloudflare Workers, Durable Objects, and Postgres, making clear tradeoffs around consistency and performance
• Own deployments across Cloudflare Workers and Fly.io, using blue-green rollouts and canary patterns
• Set a high bar for reliability, monitoring, and incident response as the platform onboards its first paying users
• Contribute across the stack, including React frontend work when needed
• Take ownership of complex technical problems end-to-end, from design through production
• Help shape engineering practices and culture as the team grows