AI Operations Engineer

About IP Fabric

Join a pioneering force in network automation!

At IP Fabric, we enable people to uncover the truth about their networks. Built by network professionals and industry experts, our innovative solutions are transforming how enterprises manage their networks. As a post-Series B company, we're expanding rapidly across Europe, the U.S., and beyond.

About The Role

IP Fabric runs its own AI Gateway: the single access point through which every engineer in the company uses AI models, from commercial APIs to open-source models we’d like to host ourselves. We are looking for an AI Ops Engineer to own it, and to make our codebase AI ready.

You will add new models to the Gateway, including self-hosted open-source models and large models served by third parties. You will keep AI usage and spend visible across all our tools and reduce cost with model routing and context compression. Alongside this, you will improve how our repositories work with AI agents: skills, agent instructions, linters, speed of our CI/CD pipelines and CI guardrails.

You will work in a small AI team reporting to Mehmet Ekmekci, together with our AI Enablement team. You will also advise colleagues across the company and work with IT, Finance, and Legal on security and data governance. We are looking for a builder: someone who takes a problem end to end, whether that means a Python service, frontend code for a dashboard, or an infrastructure change. Strong production engineering is the foundation for this role, and you should already use AI coding tools in your daily work.

What You’ll Do

• Own the AI Gateway: follow new releases, ship fixes and features, and keep it reliable for the whole company.

• Deploy and serve open-source models, and connect third-party hosted models through the Gateway when they are too large for our infrastructure. Follow developments in the model landscape and recommend what to adopt.

• Aggregate AI spend across our tools, build dashboards on top of the Gateway, and reduce cost through model routing and context compression.

• Make our repositories agent-ready: write and maintain skills and agent instruction files (AGENTS.md, CLAUDE.md), improve linters and CI guardrails, and add capabilities to our software factory.

• Support engineers in using AI tools effectively and improve the AI developer experience.

• Work with IT, Finance, and Legal to follow good security and data-governance practices.

• Contribute to AI features in the IP Fabric product together with the AI team.

What You'll Need

• Professional experience building and maintaining production software, with sound design, testing, and debugging skills. Python is our main backend language.

• A builder mindset: you are comfortable working across the stack, including frontend code for dashboards and internal tools, and infrastructure and deployment changes.

• Experience deploying and operating services in production: containers, CI/CD, and observability.

• Daily, hands-on use of AI coding agents such as Claude Code, Cursor, or Codex, and a clear view of what they do well and where they fail.

• Practical experience integrating APIs and handling authentication, rate limits, and failures across system boundaries.

• You keep up with AI developments and form your own opinions about new models and tools.

• Clear written and spoken English, including the ability to explain technical choices to people outside engineering

Bonus points if you have

• Experience serving LLMs (vLLM, Ollama, TGI ) and sizing GPU infrastructure.

• Experience with LLM gateways or proxies (LiteLLM, Portkey, or similar) and model routing.

• Experience with usage and cost analytics.

• Frontend experience (for example React and TypeScript) for internal tools and dashboards.

• Experience building MCP servers, agent skills, or agent workflows.

• Awareness of security and data-governance requirements (SOC 2, ISO 27001).

Level and growth

We are considering candidates at L2 and L3. At L2, you will own the AI Gateway and agentic-readiness work, with support on prioritisation and on cross-company governance topics. At L3, you will also lead those conversations with IT, Finance, and Legal yourself and set the technical direction within your area.

At either level, you stay responsible for the usefulness and maintainability of what you build. Your scope grows as you show dependable delivery and sound judgement.

Benefits & Perks

• 25 days of holidays + 5 flexi-days.

• Pluxee Flexi Card (up to 16 000 CZK per year).

• Anniversary rewards.

• Collaboration with diverse, international teams.

• A pet-friendly office at IP Pavlova.

• Complementary and yummy snacks, coffee, brew and refreshments.

• Regular team and company events.

Join us to experience the unique culture of a founder-led startup, where from top to bottom everyone is hands-on and has a chance to make a tangible impact on influential enterprises worldwide. Being part of IP Fabric means being part of a flexible environment that prioritizes work-life balance and growth opportunities.