SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 176,000 - 264,000 / annual
Klaviyo is seeking a Lead Engineer for Applied AI to set technical and product direction for a core area of their Customer Agent platform. The Customer Agent team is building a conversational AI system that enables brands to serve customers at scale beyond what human support teams can achieve. This is a hands-on leadership role where you'll own complex, ambiguous problems across the full agentic product stack—from orchestration to governance—while staying deeply involved in solving the hardest technical challenges yourself.
You will set technical and product direction for your area from architecture through production, and contribute to the platform's overall direction. Key responsibilities include: taking on the hardest technical problems such as orchestration, evaluation, guardrails, memory & context management, and failure handling for non-deterministic systems; writing and shipping code, reviewing designs, and making critical calls when there's no obvious right answer; defining patterns that other engineers adopt and mentoring through design reviews rather than direct management; partnering with product, design, data science, and go-to-market leaders to shape what gets built; and evaluating emerging AI technologies to bring promising ones into production.
The role is based in Boston and requires in-office work. The team is past the demo stage, shipping changes against live customer traffic, measuring quality with real evaluation frameworks, and treating reliability as a product feature. You'll have the speed and ownership of a startup backed by the scale and resources of an innovative tech company.
REQUIREMENTS:
- Proven experience building, scaling, and supporting production agentic systems (not just prototypes): real orchestration, evaluation frameworks, guardrails, and non-deterministic failure handling. Must have owned your part through launch, incidents, and operational reality post-demo.
- Deep knowledge of production agent challenges: securing against misuse and abuse, and operational experience keeping non-deterministic systems reliable as usage grows.
- Prior ownership of technical and product direction for a significant area (not just individual components). Must be able to point to something you designed and championed that shipped and that other engineers built upon.
- Hands-on approach: writing code, reviewing architecture decisions, and debugging production issues yourself—not delegating the hardest problems.
- Your patterns and designs are reused by other engineers; you've unblocked many others' projects, not just your own.
- Strong communication of complex technical trade-offs across engineering and product audiences; ability to turn undefined problems into plans others rally behind.
NICE TO HAVES:
- Experience with multi-tenant agent platforms at production scale where external customers configure agent behavior on shared infrastructure.
- Background building 0-to-1 products or working in startup environments.
- Track record with production evaluation systems, AI observability, or human-in-the-loop workflows for LLM-powered products.
