AI Product Engineer building production agents, MCP integrations, and developer tools for ClickHouse’s open-source ClickStack observability platform. Improving incident investigation, telemetry analysis, and agent reliability.
Responsibilities
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
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
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
Senior engineer evaluating OpenAI Codex, Claude Code, and Cursor interactions. Providing rigorous written and video feedback on AI - assisted software engineering quality.
Senior Software Developer building scalable, distributed network management software for Auvik, a cloud - based IT infrastructure platform. Designing microservices, Kubernetes deployments, Kafka systems, and reliable collector code.
Software Developer designing, testing, and maintaining secure applications for Multiview, an ERP and financial software company. Collaborating across teams and using AI coding agents to improve client - focused products.
Senior Software Developer delivering compliant multi - region applications and AWS infrastructure. Supporting MaintainX’s mobile - first work - execution platform for industrial and frontline teams.
Senior Software Engineer building Dentrix Ascend, Henry Schein One’s cloud - based dental practice management platform. Developing scalable Java services and improving reliability for US dental practices.
Fullstack developer building web applications, Cloud Native services, and back - end integrations at Mirego. Contributing to architecture, DevOps, AI - assisted development, and client solutions.
Senior CXE Engineer building Amazon Connect, Bedrock, and serverless contact - center solutions for Caylent. Delivering AI agents, migrations, analytics, and customer - facing implementations.
Senior Software Engineer building Snout’s veterinary wellness platform for clinics and pet owners. Developing full - stack features and operating reliable SaaS infrastructure.
Principal Software Engineer shaping Snout’s veterinary wellness platform, payments, and data systems. Leading architecture, full - stack development, DevOps, and cross - team engineering initiatives.
Staff Software Engineer defining architecture and shipping AI - powered products at Senpilot. Building intelligent systems that help utilities improve grid safety, resilience, and efficiency.