Machine Learning Engineer

Who we are Cancierge® is a health-tech startup building the lifetime AI platform for oncology and longevity. We support cancer patients, their families and clinicians with AI-driven guidance, from diagnosis through treatment and into long-term health. Patients, clinics and clinical studies feed a growing longitudinal data platform; medical knowledge from leading oncologists is at the core of everything we build. We are a senior, mission-driven team. The atmosphere is relaxed and direct: flat hierarchy, no corporate theatre, passionate discussions welcome and a mission that matters. We build a regulated medical product (EU MDR), so quality and clean engineering are not optional extras; they are how we protect patients. What you will do You will be the engineering backbone of our AI core - turning medical logic designed by our Head of AI and clinical experts into clean, tested, production-grade machine learning code, embedded in the engineering process run by our CTO. - Build: own the implementation of our AI core, from prototype logic to clean, modular, testable production code - Evaluate: design and maintain evaluation harnesses, choice of metrics, reproducibility, multiple setups - Data: build and run data pipelines for text data, including data cleaning - Train: run and improve ML training and tuning (hyperparameters, learning rates, overfitting control) - Connect: work hand in hand with our medical/logic layer on one side and our engineering and infrastructure team on the other - you are the bridge between the two What you bring - Strong Python: you write clean, modular, testable code - Solid PyTorch: you understand the framework and the theory behind it - Hands-on ML experience: hyperparameters, overfitting, learning rates and friends - Experience building eval harnesses: choice of metrics, reproducibility, different setups - Experience with data pipelines for text data, including cleaning and augmentation - Basic Linux server administration, including Docker - Good spoken and written English, our working language across the team Nice to have - Natural Language Processing background - GPU programming - Model fine-tuning experience with LLMs - Rust What we offer - A mission with real impact: helping people through one of the hardest journeys there is - €80,000–90,000 gross per year, depending on experience - Home-office first: you work remotely, with fixed team days each month at our office near Aachen (DE/NL border region) - A senior team you can learn from, experienced founders, world-class clinical advisors, engineers who care about craft - Real ownership: your code is the AI core of the product, not a cog in a machine - A culture of respect, trust and commitment ... and we don’t take ourselves too seriously How we hire No cover letter needed. Send us your CV or LinkedIn profile plus anything you are proud of (GitHub, a project, a paper). Our process: a 30-minute intro call, a technical deep-dive with our CTO, a conversation with our Head of AI and CEO - then a decision within days, not weeks.