AI Product Engineer - Clickstack

ClickHouse ClickHouse · Data AI · United States · Engineering

AI Product Engineer to build agentic capabilities on top of a petabyte-scale observability platform, with a focus on developer experience. The role involves building agents that investigate incidents, writing reusable skills, owning the agent stack end-to-end, and making ClickStack a platform for AI workloads.

What you'd actually do

  1. Build agents that investigate incidents.
  2. Write skills, not just prompts.
  3. Own the agent stack end-to-end.
  4. Make ClickStack a great place to run AI workloads.
  5. Work in the open.

Skills

Required

  • 5+ years of software engineering experience
  • 1–2 years on LLM-powered systems or agents in production
  • Strong backend skills in TypeScript/Node.js and/or Python
  • Hands-on experience building agents: multi-step tool use, planning, memory, error recovery
  • Experience designing skills
  • Experience with MCP
  • Strong evals practice
  • SQL proficiency
  • Comfort with Docker and Kubernetes
  • Active in open source and the developer community

Nice to have

  • Built or operated production agents in observability, incident response, or SRE
  • Strong opinions on agent observability
  • Experience with prompt caching, context compaction, or other techniques relevant to running agents on production telemetry volumes
  • Experience with columnar databases and event ingestion pipelines
  • Contributed to or maintained an open source AI/agent project
  • Familiarity with Go, Rust, or other systems languages for integrations and high-throughput infra

What the JD emphasized

  • building agents
  • agent stack end-to-end
  • agentic capabilities
  • agentic systems
  • production agents
  • LLM-powered systems or agents in production
  • building agents: multi-step tool use, planning, memory, error recovery
  • shipped them and dealt with the failure modes
  • building servers, designing tools, and thinking through auth, scoping, and observability for agentic systems
  • strong evals practice
  • agent observability

Other signals

  • building agentic capabilities
  • focus on developer experience
  • own the agent stack end-to-end
  • make ClickStack a great place to run AI workloads