Machine Learning Engineer (m/f/x)

<h1>Senior Machine Learning Engineer (m/w/d)</h1> <p>Four models in production today. Fifteen to twenty by mid-2027. The shared pipeline that gets them there has to hold — and you own everything after handoff: packaging, deployment, drift detection, and the call on whether a model is fit to serve.</p> <p><strong>Location:</strong> Berlin Schöneberg — you work from our office, hybrid with 3 days office and 2 days home office.</p> <h3>About us</h3> <p>CarOnSale is the AI-powered platform for B2B used car trading in Europe. Over 40,000 buyers from more than 20 countries trade on our platform — and 85% of inventory is exclusive to us. We connect software, pricing intelligence, logistics and financing in one layer — as the operating system for an entire industry.</p> <p><em><strong>One Platform. One Profit Engine.</strong></em></p> <h3>The platform you build in</h3> <p>Our machine learning runs on one shared, central platform — not a separate pipeline per model. Five canonical stages: data extraction, validation, transformation, training and evaluation. A Snowflake data warehouse feeds a SageMaker managed feature store, and models reach production through governed CI/CD promotion lanes on Terraform-managed AWS infrastructure. Your job is to build inside it and make it stronger, so the next model costs less to ship than the last one.</p> <h3>Your responsibilities</h3> <ul> <li>You own models from handoff through to production: packaging, deployment, monitoring, and the decision on whether a model is ready to serve</li> <li>You keep production models reliable — drift detection, performance monitoring, alerting and incident response when something moves</li> <li>You own the serving and inference path: fitted pipeline artifacts, inference entry points, monitoring hooks and feature-store parity</li> <li>You review model design and evaluation methodology before anything ships, and catch data leakage, backward-window errors and weak evaluation during development, while they are still cheap to fix</li> <li>You extend the shared platform so it stays useful for every model, without project-specific logic leaking into shared code</li> <li>You set the engineering standards the platform runs on as it scales across the organisation</li> </ul> <h3>What you bring</h3> <ul> <li>2+ years in production machine learning engineering, with real ownership of models after handoff — not only training them</li> <li>Strong Python: typed, tested, production-grade code, and you review the work of others</li> <li>Enough machine learning depth to challenge a pipeline on problem framing, feature engineering, model selection and evaluation methodology</li> <li>Hands-on experience with a managed ML pla