Senior AI Engineer, Agents and Platform (f/m/d) — Opportunihub
Job

Senior AI Engineer, Agents and Platform (f/m/d)

Xu De · Berlin

At a glance

Type
Job
Organisation
Xu De
Location
Berlin
Work mode
On-site
Deadline
Rolling / not stated
Posted
11 Oct 2026

About this job

<br><strong>Your mission</strong><p><br><br><span style="font-size:30px;"><strong><span style="color:rgb(0,0,0);">Join anzel</span></strong></span><span style="font-size:30px;color:rgb(0,0,0);"><strong> - The AI for the business of sport. </strong></span><span style="color:rgb(0,0,0);"><br></span><br><span style="color:rgb(0,0,0);"><br></span><span style="font-size:18px;color:rgb(40,50,78);">Clubs, leagues and federations hold deep commercial knowledge, but most of it sits in spreadsheets and in the heads of a few experts. anzel turns that knowledge into finished work: sponsor ROI reports, pitch narratives, pricing analyses, partner fit assessments.</span><span style="color:rgb(40,50,78);"><br></span><span style="font-size:18px;color:rgb(40,50,78);">Sports business experts who have done this work in sport write the skills in plain language. Agents do the work over a knowledge base those experts have checked. Nothing reaches a customer until it passes its tests. Think of anzel as an experienced senior colleague who has done this many times before.<br> <br><br></span><span style="font-size:24px;color:rgb(40,50,78);"><strong>The role</strong></span><span style="font-size:18px;color:rgb(40,50,78);"><br>In this role you own the platform every anzel agent runs on, and you set its architecture: what we build, what we buy, what we retire, written down so people and agents work from the same decisions. At anzel, AI writes most of our code and engineers guide it, so you build alongside a small senior team, close to the customer.<br></span><span style="color:rgb(40,50,78);"><br></span><span style="font-size:18px;color:rgb(40,50,78);">The hard part isn't the demo. It's making agents dependable for many customers at once: correct answers, each customer's data kept separate, and work you'd trust with a real sponsorship deal.<br><br> <br></span><span style="font-size:24px;color:rgb(40,50,78);"><strong>What you’ll own</strong></span><span style="font-size:18px;color:rgb(40,50,78);"><br></span><ul><li style="font-size:18px;text-align:justify;color:rgb(40,50,78);"><strong>The harness.</strong> How a skill written in plain language becomes a reliable agent: tools, orchestration, long running work that resumes after a failure, memory and context, retrieval, structured output, model routing, fallbacks and rollback. Models and providers sit behind our own interfaces, so we never depend on one vendor.</li></ul><span style="font-size:18px;color:rgb(40,50,78);"> <br></span><ul><li style="font-size:18px;text-align:justify;color:rgb(40,50,78);"><strong>Tools and MCP.</strong> The tool layer our agents use, which tools each agent gets, how they're versioned, and how access is scoped and logged per customer.</li></ul><span style="font-size:18px;color:rgb(40,50,78);"> <br></span><ul><li style="font-size:18px;text-align:justify;color:rgb(40,50,78);"><strong>Safe agents and separate data, with our head of engineering,</strong> who owns infrastructure, security and compliance. Each customer's data is isolated, every tool has only the access it needs, prompt injection is defended against, and every agent's actions are recorded.</li></ul><span style="font-size:18px;color:rgb(40,50,78);"> <br></span><ul><li style="font-size:18px;text-align:justify;color:rgb(40,50,78);"><strong>Quality in the pipeline,</strong> evaluations run on every change. The test sets come from our practitioners and our evaluation engineer, so nobody marks their own work. Every run is traced, with the cost and time of each piece of work visible.</li></ul><span style="font-size:18px;color:rgb(40,50,78);"> <br></span><ul><li style="font-size:18px;text-align:justify;color:rgb(40,50,78);"><strong>The engineering system,</strong> continuous delivery, review with coding agents doing the first pass, and releases that roll back in minutes. You lead by building, with clear decisions and fast, kind reviews.</li></ul></p><br><strong>Your profile</strong><p><br><ul><li style="font-size:18px;color:rgb(40,50,78);"><strong>Eight or more years building and running production software,</strong> or the equivalent built on your own. <strong>Real backend depth,</strong> APIs, a relational database, queues, long running workflows.<br><br></li><li style="font-size:18px;color:rgb(40,50,78);"><strong>Language model products that real users relied on,</strong> you can tell us about one that failed and what you changed.<br><br></li><li style="font-size:18px;color:rgb(40,50,78);"><strong>Retrieval that works, agents beyond a demo,</strong> and the judgment to know when an agent is the wrong tool.<br><br></li><li style="font-size:18px;color:rgb(40,50,78);"><strong>Evaluations that proved whether a change helped, y</strong>ou distrust a passing test until you know what would make it fail.<br><br></li><li style="font-size:18px;color:rgb(40,50,78);"><strong>Coding agents every day,</strong> several at once, without shipping code nobody understands.<br><br></li><li style="font-size:18px;color:rgb(40,50,78);"><strong>A security mindset</strong> <strong>from running systems </strong>that held customer data.<br><br></li><li style="font-size:18px;color:rgb(40,50,78);"><strong>Something you've built</strong> that you can show us.<br><br></li><li style="font-size:18px;color:rgb(40,50,78);"><strong>Professional English; </strong>German is a plus.</li></ul></p><br><strong>Why us?</strong><p><span style="font-size:15px;color:rgb(40,50,78);"><br></span><ul><li style="font-size:18px;color:rgb(40,50,78);"><strong>You own the platform of a new product,</strong> with real customers from day one.<br><br></li><li style="font-size:18px;color:rgb(40,50,78);"><strong>A small senior team,</strong> almost no bureaucracy, your own machine and your own choice of tools.<br><br></li><li style="font-size:18px;color:rgb(40,50,78);"><strong>The work matters,</strong> it helps sport close better deals, price with confidence and put more money back into the game.<br><br></li><li style="font-size:18px;color:rgb(40,50,78);"><strong>Startup energy with backing, </strong>You get the pace of a startup, supported by XU Group's experience and network.<br><br></li><li style="font-size:18px;color:rgb(40,50,78);"><strong>A strong package, </strong>highly competitive pay that reflects the seniority and responsibility of the role.</li></ul></p><p>Find <a href="https://www.arbeitnow.com">Jobs in Germany</a> on Arbeitnow</a>

How to apply

  1. 1 Read the full details above and confirm you meet the eligibility criteria.
  2. 2 Prepare your documents — an updated CV, and any cover letter, proposal or certificates required.
  3. 3 Click Apply on official site to complete your application on Xu De’s official page.
  4. 4 Submit as early as possible — many close once filled.
Apply on official site

Sourced from arbeitnow. Always verify details on the official website. Opportunihub never charges you to apply.

Frequently asked questions

How do I apply for Senior AI Engineer, Agents and Platform (f/m/d)?

Review the full details and eligibility on this page, prepare your documents, then use the “Apply on official site” button to complete your application on Xu De’s official page.

Is this opportunity remote or location-based?

This opportunity is based in Berlin. Check the official listing for any relocation or on-site requirements.

Is Senior AI Engineer, Agents and Platform (f/m/d) free to apply for?

Opportunihub lists this Job for free. Legitimate Jobs do not ask for payment to apply — never pay a fee to submit an application.