You are a senior backend engineer who has moved well past following patterns and into setting them. You're comfortable owning architectural decisions on novel infrastructure — the kind where the right answer isn't obvious and the stakes are real. You think in systems, spot failure modes early, and hold a high bar for production quality without letting perfect block good. The 80/20 mindset comes naturally: you know when to go deep and when to ship.
You've likely come from a startup or high-velocity environment where shipping fast wasn't a culture slogan — it was survival. You know how to cut scope without cutting corners, move from zero to production without a safety net, and iterate quickly on systems that are still finding their shape.
You're genuinely curious about the AI and LLM space — not as a trend to track, but as a domain where you've already done hands-on integration work and want to go further. AI tools aren't an afterthought in how you work — you use them daily, whether that's Claude Code, Cursor, GitHub Copilot, or OpenAI Codex, and you've developed real judgment about where they accelerate work and where they don't. You operate with low ego, share context freely, and thrive in an environment where autonomy and accountability go hand in hand. Ambiguity doesn't slow you down — it's where you do your best work.
- Strong Go programming skills with a track record of building and operating production backend services
- Hands-on AWS experience — designing, deploying, and operating cloud-native services at scale
- Experience integrating LLMs, AI models or tool-calling systems into production applications
- Familiarity with agentic architectures and protocols such as MCP, A2A
- A systems mindset, with attention to reliability, scalability, performance and security
- Experience with CI/CD, automated testing and production observability
- A record of working across product and platform teams to deliver outcomes end-to-end
- Regular, thoughtful use of AI coding tools as part of your development workflow
- Hands-on experience building agentic AI systems that use tools and execute multi-step workflows
- Experience building or maintaining event-sourced systems
- Python programming skills
- Experience with AI or ML infrastructure and developer productivity tooling
Your Typical Day
No two days look exactly the same. You might design a new capability for the agent runtime, improve how models and tools are orchestrated, investigate a production reliability issue, or take an integration from an early prototype to a secure, observable service.
You’ll spend much of your time building in Go, reviewing code and making architectural decisions with the team. You’ll also work closely with product, platform and AI colleagues to shape requirements, test ideas and ship them safely. Along the way, you’ll improve the testing, deployment and observability foundations that let the team move quickly with confidence.
