Senior Software Engineer, Agent Runtime & Customer Workflows
Klaviyo · Boston, MA
About this role
**Senior Software Engineer, Agent Runtime & Customer Workflows (Customer Agent) — Klaviyo** Klaviyo is building AI-native conversational experiences that help businesses create and execute better customer experiences at scale. In this role, you’ll design and build scalable backend systems and AI-powered product experiences that enable agents to reason, retrieve context, use tools, and take reliable action on behalf of customers. --- ## How You Will Make a Difference - Design and build reliable, scalable backend systems and APIs powering AI-driven customer experiences. - Build and evolve production agentic systems (tool use, orchestration, context management, retrieval, structured outputs, multi-step workflows). - Solve applied AI problems across retrieval/RAG, grounding, model selection, hallucination mitigation, and hybrid vs. deterministic approaches. - Develop evaluation strategies (representative datasets, automated + human evaluation, regression testing, error analysis, production signals). - Improve production reliability with guardrails, fallbacks, retries, observability, monitoring, and failure handling. - Build asynchronous and distributed processing workflows for high-volume AI workloads. - Participate in an on-call rotation and help diagnose/mitigate production incidents. - Work with external customers and cross-functional partners to understand workflows, identify pain points, and translate feedback into improvements. - Monitor shipped experiences using customer behavior, quality metrics, and system performance to guide iteration. --- ## Who You Are - **5–7 years** of professional software engineering experience, with strong backend + distributed systems foundations. - Hands-on experience building and deploying **generative AI or agentic AI applications in production** for real users. - Proficient in **Python** and modern backend frameworks such as **FastAPI** or **Django**. - Experience with asynchronous processing and distributed task/event systems (e.g., **Celery, Kafka, SQS, RabbitMQ, Redis**). - Strong knowledge of databases, data modeling, APIs, and persistence patterns. - Comfortable in cloud-native environments (e.g., **AWS, containers, Kubernetes, CI/CD**). - Ability to reason about tradeoffs across **quality, latency, cost, reliability, and complexity**. - Can operate independently in ambiguous environments and make pragmatic decisions. - Experience working directly with external customers to improve products. - Strong interest in shipping useful, reliable products in a rapidly evolving technical space. --- ## Nice to Have - Experience training/fine-tuning/distilling/adapting ML or language models for production. - Experience with reinforcement learning or feedback-driven optimization. - Experience building evaluation infrastructure (LLM-as-judge, evaluator calibration, benchmark suites, AI quality platforms). - Experience operating AI systems at substantial scale (optimizing inference cost, latency, throughput). --- ## Compensation (US Locations) **Base Pay Range:** **$148,000 — $222,000 USD** --- *This role may require up to **10% travel** for onboarding, client/partner work (if applicable), team meetings, and industry events.*
Listing freshness
CronJobs last confirmed this listing 1h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.