AI Engineer | Interloom

About Interloom

Interloom is building the first navigation system for work.

For thirty years, enterprise software has forced fluid, human work into rigid forms, tickets, and CRMs. Yet most of what actually happens inside a company, the decisions, the escalations, the problem-solving, happens outside those systems. Roughly 70% of operational knowledge is never written down. It lives in inbox threads, support tickets, and the heads of experienced people. Interloom changes that. We capture how expert teams actually resolve work and turn it into a living context graph, a permanent memory layer that lets AI agents act on your company's real, proven decisions instead of generic training data.

We put subject-matter experts, not developers, in control. Everything in Interloom is built from natural language: a procedure is written the way you would explain it to a new colleague, and an agent is briefed the way you would brief a contractor. We are already deployed at enterprises like Zurich Insurance, JLL, and Fiege, across facility management, insurance, banking, logistics, energy, and ITSM.

We are a team of engineers, operators, and researchers across Munich and Berlin. In March 2026 we raised a $16.5M seed round led by DN Capital, with participation from Bek Ventures and Air Street Capital, to expand across enterprise customers and accelerate our go-to-market. If you want to do the best work of your life on a hard, real problem, we want to hear from you.

How we work

• Experts in control. The people closest to the work design it. We build for the operator, not the developer, and we work the same way internally.
• Describe, then automate. If it can be described clearly, it can be built. We value precise thinking and plain language over jargon and ceremony.
• Context compounds. We do not let knowledge disappear. We write things down, learn from every case, and make the next decision better than the last.
• Humans make the call. Agents handle the routine so people can focus on the highest-value work and the decisions that matter.
• Small teams, real ownership. Lean, autonomous teams with minimal bureaucracy. You own outcomes, not tasks.
• Ship to learn. We put working software in front of real users early and let evidence, not opinion, decide what comes next.

About the role

Interloom builds AI-powered operations software for enterprises.

We help organizations understand how work actually happens, capture expert knowledge, and automate complex workflows with AI agents that have real operational context.

Most companies run on knowledge that never fully makes it into documentation: decisions hidden in tickets, emails, workflows, internal tools, and the heads of experienced employees. Interloom turns that operational context into structured memory that AI systems can use reliably.

We’re building software for a future where humans and AI agents work together across complex enterprise workflows. That means our platform has to be secure, reliable, observable, and able to scale across customers, clouds, regions, and workloads.

You’ll be part of the AI Engineering team, working end-to-end on the systems that make our agents capable, reliable, and safe. The work is practical and close to users: details in context building, tool design, and retry/recovery paths are often what determines whether an agent works reliably in production.

What you’ll do

• Build and refine agent capabilities through tools, skills, and integrations, designed to be safe, observable, and easy for an LLM to use correctly.
• Improve the agent runtime: tool calling, orchestration, error handling, and handoffs.
• Spot failure modes and improve reliability so agents fail safely instead of silently, and gracefully recover where possible.
• Grow our evaluation framework — the scenarios, graders, and tooling we use to test agents across multi-step workflows.

What we’re looking for

• Professional backend engineering experience, ideally with Python.
• You write tested, type-checked, maintainable code and care about quality and long-term sustainability.
• Solid understanding of relational databases (Postgres/SQL) and API design.
• Curious about LLMs beyond prompting: tool calling, context design, evaluations, observability, and failure modes.
• You can take a bounded problem, make a small plan, ship the change, and communicate tradeoffs clearly.
• You like working close to product problems, not only on isolated research tasks.
• Practical AI/LLM experience, exposure to LLM tooling (context engineering, RAG, evaluations), experience with Temporal or other durable workflow engines, and comfort using metrics to improve quality are all especially helpful.

We are flexible on level. This role is a good fit if you have solid software engineering fundamentals and have a deep interest in building production agent systems.

Compensation and benefits

• 💰 Salary: €65,000 to €85,000. Final offer depends on experience and level.
• 📈 VSOP: Virtual stock options, so you share in the upside you help build.
• 💻 Pick your own workstation and hardware. We give you the tools you need so nothing slows you down.
• 🏢 Cozy, comfortable offices in Munich and Berlin.
• 🔄 Hybrid work mode, so you can work in the way that gets your best performance.
• 🌍 Annual company retreats to spend real time with the team.
• 🤖 Groundbreaking work in AI and ML, pushing the boundaries of what agents can do.
• 👥 A collaborative, high-trust environment built for high performance.
• 🚀 Professional growth with clear pathways to leadership as we scale.

Location

This role is hybrid or remote. If you’re in Berlin, you can work hybrid out of our office (Leuschnerdamm 13); otherwise you’re welcome to work fully remotely. Either way, working hours align to Central European Time, with occasional travel to the team and offsites.

Application

We'd love to hear from you. To start the conversation, tell us briefly why Interloom and what you'd want to work on.

To apply, send us:

1. A short note on why Interloom and what you'd want to work on.
2. Your resume or CV.

Email everything to jobs@interloom.com. We read every application.

Interloom is an equal-opportunity employer. We hire for talent and judgment, not background or location.