AI Product Engineer - ClickStack

About ClickHouse

ClickHouse, recognized on the 2025 Forbes Cloud 100 list, is a rapidly expanding private cloud company specializing in real-time analytics, data warehousing, observability, and AI workloads, serving over 4,000 customers with remarkable growth. Supported by a recent $400M Series D funding and prominent clients like Meta, Sony, and Tesla, the company is on a mission to revolutionize data usage.

Role Overview

Join ClickHouse as an AI Product Engineer focused on developing agentic functionalities within ClickStack, an open-source observability platform uniting logs, metrics, traces, and session replays. Your work will center around creating intelligent agent systems that diagnose incidents autonomously, enhancing developer experience at a petabyte-scale observability level.

Key Responsibilities

• Create investigatory agents that detect anomalies and explain production issues using ClickStack.
• Develop reusable skill libraries encoding debugging, root cause analysis, query writing, and incident responses to provide agents structured playbooks.
• Lead the full agent stack management including context engineering, tool design, evaluation, tracing, and cost optimization, ensuring production reliability.
• Enhance ClickStack as an AI workload platform by building MCP servers, SDKs, and integrations enabling agents to interact with telemetry and maintain observability.
• Collaborate openly with open-source contributors and clients to troubleshoot and incorporate feedback into the product.
• Address challenges such as latency, operational cost, context window constraints, evaluation coverage, and hallucinations in telemetry data.

Candidate Profile

• Experienced in building agents with strong opinions on context engineering, tool design, skill/tool integration, evaluation scope, and limitations of popular frameworks.
• Produces production-grade systems focused on latency at the 99th percentile, cost efficiency, and autonomous operation.
• Demonstrates rapid iteration with frequent deployments and learns effectively from failures.
• Values developer experience and possesses clear insights into excellent developer tools.
• Thrives in ambiguous situations and takes ownership of their domain.

Required Qualifications and Skills

• Minimum of 5 years in software engineering, including 1-2 years working with LLM-powered systems or agents in production environments.
• Proficient backend development skills in TypeScript/Node.js and/or Python; comfortable working with both languages.
• Hands-on experience with building advanced agents featuring multi-step tool usage, planning, memory capabilities, and error handling.
• Expertise in designing skills using Markdown-based workflows and frameworks similar to Anthropic.
• Experience with MCP server development including authentication, scoping, and observability considerations.
• Strong evaluation practices, including use of golden datasets, LLM-based judgment, and regression detection.
• Fluent in SQL with ability to write queries for ClickHouse.
• Familiarity with Docker and Kubernetes container orchestration.
• Active participation in open-source and developer communities.

Desirable Bonuses

• Experience operating production agents within observability, incident response, or SRE domains.
• In-depth knowledge and strong opinions on agent observability related to tracing, cost attribution, evaluation pipelines, and OpenTelemetry integration.
• Skills in prompt caching, context compaction or other techniques relevant to scalable agent operation on real telemetry data.
• Experience with columnar databases and event ingestion systems.
• Contribution to or maintenance of open source AI/agent projects.
• Familiarity with systems programming languages like Go or Rust for integrations and high-throughput infrastructure.

Compensation and Work Environment

Salary ranges are provided based on location and individual factors such as experience, qualifications, and performance, with potential adjustments over time. Reach out for pay transparency inquiries at paytransparency@clickhouse.com.

Benefits

• Flexible work environment supporting remote work globally across 20+ countries.
• Employer contributions towards healthcare coverage.
• Equity participation through stock options for all new hires.
• Generous and flexible time-off policies, varying by country.
• Remote employees receive a $500 home office setup allowance.
• Company-wide global gatherings to foster in-person engagement.

Culture and Diversity

Contribute meaningfully to shaping the culture of a fast-growing startup dedicated to inclusivity and equal opportunity employment. ClickHouse strictly prohibits discrimination and harassment based on protected characteristics and maintains a detailed privacy policy.