Senior Machine Learning Engineer

Make a measurable and mission-critical impact. Bring your unique talents and experience to a leading company in Industrial IoT ( IIoT ) solutions. Grow your passion into a rewarding profession by joining a dynamic and expanding organization. You’ll play a vital role that supports your success and helps drive safe, efficient, and reliable operations across industries worldwide. Where you’ll work: This is a hybrid role based out of our Porto office. In practice, most of your work can be done remotely, with occasional in-office time in Porto for team collaboration — a flexibility our engineers consistently tell us they value. Job Duties and Responsibilities: You will own machine learning solutions end to end — from framing the business problem to running models reliably in production — built on real-time telemetry from industrial IoT sensors deployed around the world. Collaborate for success Own machine learning projects end to end: plan the roadmap, frame the problem, build the pipelines, and take solutions through to production. Translate business goals into ML solutions, and explain results, limitations and uncertainty to business stakeholders in terms they can act on. Make the technical decisions, contribute significantly to the implementation, and mentor other engineers through code review and design discussion. This is a hands-on role. Build ML-powered solutions Deliver forecasting, classification and anomaly detection on time series from industrial IoT sensors reporting in real time from sites across the globe. Work with the realities of sensor data: gaps, drift, scarce labels, and a device population that keeps evolving. Run what you build — monitoring, drift detection and retraining — and shape the data pipelines your models depend on. Engineer with AI assistance Use agentic coding tools — Claude Code, Copilot, Cursor and similar — as a normal part of daily delivery. Hold AI-generated code to the same bar as any other code. You are accountable for what you ship. Structure repositories, tests and documentation so both people and agents can work in them effectively, and share the patterns and guardrails that work so the team's baseline rises. Apply Anova's AI Handbook guidance on model risk and human-in-the-loop validation to any model whose output reaches a customer or drives an automated action. Advocate for quality Contribute to and continuously adapt best practices and Ways of Working across data engineering, machine learning and MLOps , so the team ships high-quality solutions that create real impact for our clients. Minimum Requirements - Bachelor's degree in Computer Science , Data Science, Engineering, or a related quantitative field or equivalent combination of education and experience 5+ years of experience in machine learning engineering or a closely related software engineering role, including hands-on production deployment (6–8 years preferred). Hands-on experience delivering production-level, cloud-native machine learning solutions. Strong Python and the engineering habits that go with it: git, code review, linters, unit tests and CI/CD pipelines are things you use daily. Strong understanding of feature engineering, ML algorithms, model training and evaluation. Solid experience across a modern ML stack: gradient boosting ( LightGBM , XGBoost ), scikit-learn, PyTorch , MLflow , and current time series tooling. Experience operating models in production: deployment, monitoring, drift detection and retraining, and a feel for the MLOps practices that make that sustainable. Fluency with agentic coding tools. Fluent in written and spoken English. Preferred Qualifications - Depth in the Azure Databricks platform: PySpark , MLflow , streaming pipelines. Experience implementing agentic workflows in production. Familiarity with MCP (Model Context Protocol) or similar patterns for exposing models as tools other agents can call directly. Domain experience in industrial, energy or IoT settings.