Machine Learning Engineer

About CarOnSale & The Role

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.

Location: Central Berlin — hybrid setup (3 days office, 2 days home office).

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. One Platform. One Profit Engine.

The Platform You Build In

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.

Your Responsibilities

• Model Ownership: Own models from handoff through to production, including packaging, deployment, monitoring, and the final decision on service readiness.
• Reliability & Monitoring: Keep production models reliable through drift detection, performance monitoring, alerting, and incident response.
• Serving Architecture: Own the serving and inference path, fitted pipeline artifacts, inference entry points, monitoring hooks, and feature-store parity.
• Quality & Governance: Review model design and evaluation methodology before deployment to catch data leakage, backward-window errors, and weak evaluation early.
• Platform Scaling: Extend the shared platform to serve every model without allowing project-specific logic to leak into shared code.
• Engineering Standards: Set the engineering standards the platform runs on as it scales across the organisation.

What You Bring

• 2+ years experience in production machine learning engineering with proven ownership of models post-handoff.
• Strong Python skills: Typed, tested, production-grade code, with experience reviewing peer code.
• ML Depth: Ability to challenge pipelines on problem framing, feature engineering, model selection, and evaluation methodology.
• MLOps & Cloud Stack: Hands-on experience with managed ML platforms (SageMaker, Vertex AI, Databricks, or Azure ML), feature stores, ML CI/CD, AWS, and Terraform.
• AI-Native Mindset: Active daily use of AI tools such as Claude, ChatGPT, or Copilot.
• Languages: C1 English (written and spoken). German is not required.

Nice to Have

• Experience with Snowflake and dbt (or willingness to learn on the job).
• Experience mentoring colleagues or conducting code reviews.
• Comfort operating in dynamic environments where answers are not yet fully defined.

What to Expect From Us

• Flexible Working: Hybrid model (3 days office / 2 days remote) plus 25 “Work from Anywhere” days per year.
• Time Off: 28 days of annual leave.
• Growth: 2× annual career & development conversations, structured onboarding with a buddy programme.
• Financial Benefits: Virtual stock options and company pension with a 20% employer contribution.
• Mobility & Wellness: Fully paid Deutschlandticket, FitX membership or Urban Sports Club subsidy.
• Perks & Culture: Modern IT setup, lived diversity (active women’s network, meditation & prayer room), and social events.