Build and operate production-grade agentic AI systems, owning agent evaluation, testing, retrieval, orchestration, monitoring, and production reliability. Design workflows with LangChain or LangGraph, create evaluation harnesses and regression gates, diagnose failures, optimize latency and cost, and establish technical standards. The role requires 6+ years of software engineering experience, including 2+ years building production LLM or agent systems, plus strong ownership and communication in an ambiguous startup environment.

Lead customer integrations by building warehouse-native or managed ClickHouse pipelines, construct semantic metadata layers, canonicalize source data into unified growth models, and act as the technical lead for enterprise deployments while partnering with AI discovery agents to accelerate onboarding and mapping.

Design, build, and maintain production-grade AI systems and agent-based workflows; own end-to-end pipelines from experimentation to deployment and monitoring; build evaluation pipelines; collaborate with product, data, and GTM; iterate quickly under ambiguity to shape the AI stack.