Senior Machine Learning Engineer

I’m working with one of the world’s largest med-tech companies as it builds the intelligence layer behind its next generation of connected-care products. They are hiring a Staff Machine Learning Engineer to lead the development of production ML systems across medication forecasting, anomaly detection, optimisation and conversational analytics. You will own problems from experimentation and model design through deployment, monitoring and adoption in real healthcare environments. What you’ll work on Build probabilistic and multi-series forecasting models that predict medication demand across products, locations and time horizons. Develop anomaly-detection systems capable of identifying unusual inventory, usage and operational patterns. Connect ML predictions with optimisation methods to produce practical recommendations rather than isolated model outputs. Evaluate classical statistical approaches against deep-learning and transformer-based forecasting architectures. Build agentic and natural-language interfaces that allow users to interrogate complex operational data. Own training pipelines, feature engineering, backtesting, calibration, uncertainty estimation and shadow-mode evaluation. Deploy reliable ML services and batch workflows on AWS using Python, Docker and Kubernetes. Create monitoring for model quality, drift, latency and production behaviour. Develop explainable outputs suitable for users operating in a high-trust, regulated environment. Provide hands-on technical leadership through architecture decisions, code reviews and mentoring. What they’re looking for Strong experience taking machine-learning systems from research and experimentation into production. Depth across time-series forecasting, demand modelling, anomaly detection or mathematical optimisation. Excellent Python and experience with PyTorch and the wider scientific Python ecosystem. Understanding of classical forecasting methods as well as modern deep-learning approaches. Experience building production ML systems on AWS, including containerised deployment and CI/CD. Strong software-engineering standards across testing, packaging, observability and reproducibility. The ownership and pace to take a complex problem from initial exploration to a working production system. This offers the scope of a greenfield AI build with the data, resources and deployment reach of a global technology organisation. It is an opportunity to remain deeply hands-on while having Staff-level influence over the architecture and engineering standards of a growing AI platform. #J-18808-Ljbffr