Staff Engineer, Applied AI (Customer Agent)

About the Team

Our Engineering team builds the AI systems that power how brands run their businesses on Klaviyo. We move fast, ship in production, and hold a high bar for what "AI-native" actually means: systems that make real judgment calls, not demos.

The Customer Agent team is one of the newest and most ambitious groups in that org, based in Boston and working in-office: we're building a conversational AI system that lets brands serve their own customers at a scale no human support team could match. We're past the demo stage: the team ships changes against live customer traffic, measures quality with real evaluation frameworks, and treats reliability as a product feature, not an afterthought.

About the Role

As a Staff Engineer, you'll set the technical and product direction for a core area of Customer Agent end to end, building a 0-to-1 agentic product with the speed and ownership of a startup, backed by the scale and resources of one of the most innovative tech companies on the East Coast, while staying hands-on with the hardest problems yourself. This is a lead-level role, with a wide footprint across our agentic product - from orchestration to governance - that grows based on where the product is when you join.

How You'll Make an Impact

• Set the technical and product direction for a core area of Customer Agent, from architecture through production, and contribute to the direction of the platform overall.
• Take on the hardest technical problems in your area: orchestration, evaluation, guardrails, memory & context, failure handling for non-deterministic systems.
• Write and ship code, review designs, and make the hard calls in your area when there’s no obvious right answer.
• Define patterns that other engineers adopt, and mentor through design reviews rather than direct management.
• Partner with product, design, data science, and go-to-market leaders to shape what gets built, not just how it’s built.
• Evaluate emerging AI technologies and bring the ones worth betting on into production.

What We're Looking For

• You've built, scaled, and supported production agentic systems, not just prototyped them: real orchestration, evals, guardrails, and non-deterministic failure handling. You've owned your part of one through launch, incidents, and the 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 owned technical and product direction for a significant area before, not just your own component, and you can point to something you designed and championed that shipped and that other engineers built on.
• You're hands-on: writing code, reviewing your own and others’ architecture decisions, and debugging production issues yourself, not delegating the hardest problems away.
• Your patterns and designs are reused by other engineers, and you've unblocked many others’ projects, not just your own.
• You communicate complex technical trade-offs clearly across engineering and product audiences, and you can turn an undefined problem into a plan others rally behind.

Nice to Haves

• Experience working on a multi-tenant agent platform at production scale, where external customers configure their own agent behavior on shared infrastructure.
• Experience building 0-to-1 products or working in startup environments.
• A track record with production evaluation systems, AI observability, or human-in-the-loop workflows for LLM-powered products.

Other Requirements

• This role may require up to 10% travel for new hire onboarding, client or partner work, team meetings, and industry events.