AI Operations Engineer

About the Team

IT Operations at ClickHouse keeps the company's internal systems, tooling, and infrastructure running securely and efficiently — from identity and endpoint management to the platforms every team relies on to do their work. This role sits on a newly formed AI Engineering function within IT Operations, created to centralize AI Ops rather than leave it disjointed across teams. The team — a Technical Lead plus one or two AI Ops Engineers — reporting to the IT Business Systems Manager, and brings the same rigor IT Ops applies to systems and infrastructure to the design, deployment, and lifecycle management of AI solutions and the agents they power.

About the Role

We are looking for an AI Ops Engineer to help build and run a new AI Ops function at ClickHouse. You will work under a Technical Lead to design, build, and maintain AI-driven solutions across the business (People, Finance, Legal, and beyond) and engineering — building integrations, maintaining agents, supporting cost visibility, and helping train the org on AI best practices. This is a hands-on execution role: you will move quickly, ship real workflows, and help the team learn what works as we centralize AI Ops for the first time.

Success

This is a net-new function; specific goals will be set with your Technical Lead. Directionally, the team is measured on:

• Measurable reduction in redundant or inefficient AI tool and model spend through right-sizing, routing, and cost visibility
• A working framework for evaluating and selecting models/tools by cost, latency, accuracy, and risk, adopted across teams
• Agents and AI workflows built, deployed, and maintained cross-functionally (People, Finance, Legal, Engineering, and beyond)
• Improved AI fluency and literacy org-wide, measured through training participation, adoption of approved tools, and reduced shadow-AI usage
• Established identity, access, audit, and lifecycle practices for AI agents that satisfy Security and GRC requirements

You Will

Build AI-Powered Solutions

• Develop and deploy solutions using LLMs, automation frameworks, and internal tooling, for both business and engineering use cases
• Integrate AI into existing systems (HRIS, ATS, ERP, procurement orchestration, ticketing, CI/CD, developer tooling) and legal infrastructure like CLM or Matter Management
• Build workflows such as document generation, data extraction, knowledge retrieval, and decision support across systems and knowledge bases
• Use modern integration standards (e.g., MCP) to give AI models and agents direct, secure access to internal knowledge and context

Support Model Evaluation

• Help test and benchmark AI models against accuracy, latency, cost, and safety criteria
• Support model risk assessments and due diligence alongside Security and GRC
• Help implement and maintain the internal model routing solution

Support Cost Visibility

• Help build dashboards and reporting for AI/LLM spend across teams and tools
• Implement tagging, monitoring, and alerting for cost anomalies
• Identify and execute on cost-optimization opportunities (prompt efficiency, caching, model right-sizing)

Maintain Agent Infrastructure

• Help provision, credential, and de-provision AI agent access
• Support deployment, versioning, monitoring, and retirement of agents
• Maintain and patch agent infrastructure and dependencies
• Help maintain audit trails and logging for agent actions

Deliver Training and Enablement

• Design and deliver company-wide AI training programs tailored to different audiences — non-technical business users through engineers
• Create lightweight playbooks, guides, templates, and reusable components for safe, effective AI adoption
• Run onboard