AI Product Engineer

ClickHouse

. Build agents that investigate incidents, surface anomalies, answer why production is broken, and use ClickStack as their substrate .

Posted 10/30/2026full-timeRemote • United Kingdom, Canada, Germany, United States, NetherlandsMid-LevelSenior💰 £90,000 - £135,000 per yearWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in building and deploying LLM-powered systems and agents, with strong backend skills in TypeScript/Node.js and Python. Proficient in SQL and ClickHouse querying, with a focus on incident response, observability, and evaluation practices.

Highest-signal resume keywords

Software Engineering ExperienceLLM-Powered Systems DevelopmentTypeScript/Node.js Backend SkillsSQL Proficiency with ClickHouseMCP Server and Tool Design

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Software EngineeringLLM-Powered SystemsTypeScriptNode.jsPythonSQLClickHouseMarkdown-Based Workflow DesignError RecoveryEvaluation Practices

Soft Skills

CollaborationProblem-SolvingCommunity Engagement

Tools & Technologies

DockerKubernetesOpenTelemetryMCPTelemetry Integration

Industry Keywords

Incident ResponseObservabilitySREAgent DevelopmentOpen Source Contributions

Tech Stack

Tools & technologies

DockerJavaScriptKubernetesNode.jsOpen SourcePythonRustSQLTypeScriptGo

About the role

Key responsibilities & impact

Build agents that investigate incidents, surface anomalies, answer why production is broken, and use ClickStack as their substrate
Build a reusable library of skills encoding debugging, root-cause analysis, ClickHouse querying, and incident response workflows
Own the agent stack end-to-end, including context engineering, tool design, evaluations, tracing, and cost management
Build MCP servers, SDKs, and integrations that enable customer agents to read telemetry, take action, and remain observable
Collaborate with open-source contributors and customers, debug their problems, and feed learnings back into the product
Address latency, cost, context-window limits, evaluation coverage, and hallucinations on real telemetry
Shape the culture of a rapidly scaling startup

Requirements

What you’ll need

5+ years of software engineering experience
1–2 years working on LLM-powered systems or agents in production
Strong backend skills in TypeScript/Node.js and/or Python; comfortable in both
Hands-on experience building and deploying agents with multi-step tool use, planning, memory, and error recovery
Experience designing skills using Markdown-based workflow encodings, Anthropic-style approaches, or similar
Experience with MCP, including building servers, designing tools, and handling auth, scoping, and observability
Strong evaluation practice, including golden sets, LLM-as-judge, and regression detection
SQL proficiency, including writing ClickHouse queries directly
Comfortable with Docker and Kubernetes
Active participation in open source and the developer community
Bonus: production agents in observability, incident response, or SRE
Bonus: agent observability experience, including tracing, cost attribution, eval pipelines, or OpenTelemetry
Bonus: prompt caching, context compaction, or similar production-agent techniques
Bonus: columnar databases and event ingestion pipelines
Bonus: contributions to or maintenance of an open-source AI/agent project
Bonus: familiarity with Go, Rust, or other systems languages for integrations and high-throughput infrastructure

Benefits

Comp & perks

Employer contributions towards healthcare
Stock options for every new team member
Flexible time off in the US
Generous time-off entitlement in other countries
USD$500 home office setup allowance for remote employees
Opportunities to engage with colleagues at company-wide offsites
Flexible work environment
Remote-friendly work arrangement