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. If you’re a close but not exact match with the description, we hope you’ll still consider applying. Want to learn more about life at Klaviyo? Visit klaviyo.com/careers to see how we empower creators to own their own destiny.

AI Engineer, Customer Agent

About the Role

At Klaviyo, we believe the future of software lies not only in tools that help people work more efficiently, but in intelligent systems that can take action, learn from outcomes, and improve customer experiences over time.

Klaviyo serves more than 167,000 customers and processes billions of consumer profiles, messages, interactions, and conversion signals. This creates a unique opportunity to build state-of-the-art AI systems that help businesses create and execute better customer experiences at scale.

We’re looking for an AI Engineer to join the Customer Agent team, Klaviyo’s AI-native conversational platform. You’ll help build scalable backend systems and AI-powered product experiences that enable agents to retrieve context, use tools, and take reliable action on behalf of customers.

This is a backend-heavy role with opportunities to contribute to user-facing experiences. You’ll independently own meaningful pieces of larger systems, contribute to technical decisions, and continue developing your depth across backend engineering, applied AI, and production reliability.

How You Will Make a Difference

• Build and improve reliable backend systems and APIs that power AI-driven customer experiences.
• Develop production agentic features involving tool use, context management, retrieval, structured outputs, orchestration, and multi-step workflows.
• Contribute to solving applied AI problems across retrieval and RAG, grounding, hallucination mitigation, model selection, and choosing between LLM-based, deterministic, or hybrid approaches.
• Build and use evaluation approaches including representative datasets, automated and human evaluation, regression testing, qualitative error analysis, and production signals.
• Improve system reliability through guardrails, retries, fallbacks, observability, monitoring, and thoughtful failure handling.
• Build asynchronous and distributed processing workflows that support AI workloads at scale.
• Participate in an on-call rotation and help diagnose, mitigate, and learn from production incidents.