Sr. Lead Engineer, Applied AI (Customer Agent)New$324K

The opportunity

At Klaviyo, we value the unique backgrounds, experiences and perspectives each Klaviyo (we call ourselves Klaviyos) brings to our workplace each and every day. We believe everyone deserves a fair shot at success and appreciate the experiences each person brings beyond the traditional job requirements.

What you'll do

  • Set the technical and product direction for Customer Agent's core platform,: from architecture through production.

  • Take on the platform's hardest technical problems personally: orchestration, evaluation, guardrails, memory & context, self-healing/improving and failure handling for non-deterministic systems.

  • Write and ship code, review designs, and make the calls other engineers can't make alone.

  • Build architecture and frameworks that other engineers and teams adopt, and: mentor through design reviews rather than direct management.

  • Partner with product, design, data science, and go-to-market leaders to shape: the roadmap, not just execute against it.

  • Evaluate emerging AI technologies and bring the ones worth betting on into production.

What they're looking for

  • You've architected, built, scaled, and supported a production agentic system: end to end, not just prototyped one: real orchestration, evals, guardrails, and non-deterministic failure handling. You've owned it through launch, scale, incidents, and the years of operational reality after the demo.
  • You've learned the hard lessons that only come from running agents in: production: securing them against misuse and abuse, and the operational scar tissue of keeping a non-deterministic system reliable as usage grows.
  • You've set technical and product direction for an entire product area before,: not just your own component, and you can point to something you designed and championed that shipped and that other teams built on.
  • You've stayed hands-on through all of it: still writing code, reviewing your own architecture decisions, and debugging production issues yourself, not delegating the hardest problems away.