Applied ML Engineer/Data Scientist

h3About grape: /h3 /brpOur entrepreneurial spirit drives us in what we do and what we are passionate about. Our mission is to become the premier health partner in the insurance business. Recognising the need for innovation in the traditional employee insurance model we are set to revolutionize the employee insurance industry. We help companies support people before and after they get sick and to make more of their time. Our insurance solutions reduce monotonous and manual work for employees, doctors, HR payroll managers. As we strive to lead a technology-driven transformation, we put employees first. /p /brpAt grape we pride ourselves on our people and our culture. We continue to grow fast and that's where you come in. Our team is dynamic, diverse and full of creative ideas. Want to join? We can't wait to get to know you! /p /brh3Our role /h3 /brpOur data and tech give us an edge in risk assessment, pricing and premium calculation. This role turns that into accurate models that support our carrier partners and our growth, builds tuned models where they beat rules and off-the-shelf LLMs in claims (triage, intervention, return-to-work, fraud), and responsibly explores how data can help employees stay healthy through grape Care. /p /brpWe're looking for an applied ML engineer / data scientist to build predictive models from the ground up on real, regulated insurance data. You'll own problems end to end, from effective-dated records to production, in a domain where correctness and responsible use genuinely matter. /p /brpStarting points include pricing and risk, portfolio monitoring, claims and payment patterns, triage and return-to-work, absence, and fraud detection. grape sits on a rich dataset, though, and you'll help find the next high-value use cases. You're candid about what the data can support, and you propose simpler approaches when they're the right answer. /p /brpThis is not an LLM role. LLM and agent workflows and document extraction sit with our engineering teams, and you'll use their outputs as features. /p /brh3What you'll do: /h3 /brul /brliBuild and validate models /li /brliOwn the full model lifecycle: feature engineering, training, evaluation, explainability, deployment, and drift monitoring. /li /brliBacktest on the historical book and run models in shadow mode alongside human decision-makers, reporting where and why they disagree. /li /brliProduce audit-ready validation and governance documentation that actuarial, compliance, and carrier partners can review. /li /brliDeploy models on grape's cloud platform within strict security and data-residency requirements for health data. /li /brliSet up experiment tracking, model versioning, and production monitoring, partnering with engineering on integration. /li /brliIdentify and prioritize high-value use cases as you explore the dataset, rather than waiting to be handed problems. /li /brliTurn ambiguous business questions into well-defined, measurable modelling. /li /brliBuild privacy, fairness, and explainability into every model that touches personal or health data, working with compliance and legal on nDSG/GDPR boundaries. /li /brliCollaborate: Explain model behavior and limits to underwriting, claims, actuarial, and compliance teams. /li /br /ul /brh3Platform and MLOps /h3 /brpDeploy models on grape's cloud platform within strict security and data-residency requirements for health data. /p /brpSet up experiment tracking, model versioning, and production monitoring, partnering with engineering on integration. /p /brh3Shape the problem space /h3 /brul /brliIdentify and prioritize high‑value use cases as you explore the dataset, rather than waiting to be handed problems. /li /brliTurn ambiguous business questions into well‑defined, measurable modelling. /li /br /ul /brh3Responsible explainable by design /h3 /brul /brliBuild privacy, fairness, and explainability into every model that touches personal or health data, working with compliance and legal on nDSG/GDPR boundaries. /li /brliModels support decisions; accountable owners make them. Pricing, reserving, and claims work requires licensed‑actuary sign-off, and any automation requires governance approval first. /li /br /ul /brh3Collaborate /h3 /brpExplain model behavior and limits to underwriting, claims, actuarial, and compliance teams. /p /brh3What you'll need: /h3 /brul /brliStrong applied ML and statistics: supervised and unsupervised learning, anomaly detection, time‑series, and survival/duration modeling. /li /brliProven experience building models on real-world, relational, effective-dated data, including imbalanced outcomes. /li /brliFluent Python (pandas, scikit‑learn, a modern ML stack) and strong SQL. /li /brliSolid grasp of validation, calibration, and explainability (e.g. SHAP). /li /brliProduction MLOps: experiment tracking, versioning, and drift monitoring. /li /brliSound judgment on data privacy and modelling. /li /brliFluent English. /li /brliBias for action, ownership, and clear cross‑functional communication. /li /br /ul /brh3Big plus: /h3 /brul /brliInsurance, actuarial, or risk modeling (pricing, reserving, loss ratios). /li /brliHealth, disability, or absence data, especially Swiss insurance (KTG, UVG); fraud detection in claims. /li /brliRegulated special‑category data under nDSG/GDPR, or model risk management. /li /brliGoogle Cloud, including security‑restricted deployments. /li /brliGerman language skills. /li /br /ul /brh3What we offer in return: /h3 /brul /brliEmpowering workplace: Join a passionate team and an empowering workplace where you are given the ownership, tools, and support to make decisions and take initiative. Together we grow and build innovative solutions. /li /brliHybrid setup: Enjoy the flexibility of our hybrid work schedule, with the freedom to work remotely or from our office in Zurich. On Thursdays, our team day, we meet together in our Zurich office. /li /brliHome office stipend: To e /li /br /ul #J-18808-Ljbffr