Machine Learning/AI Research Engineer (Post-doc)

Machine Learning/AI Research Engineer (Post-doc) This role has been designed as 'Hybrid' with a requirement that you will work on average 2 days per week from an HPE office. Who We Are: Hewlett Packard Enterprise is the global edge-to-cloud company advancing the way people live and work. We help companies connect, protect, analyze, and act on their data and applications wherever they live, from edge to cloud, so they can turn insights into outcomes at the speed required to thrive in today’s complex world. Our culture thrives on finding new and better ways to accelerate what’s next. We know varied backgrounds are valued and succeed here. We have the flexibility to manage our work and personal needs. We make bold moves, together, and are a force for good. If you are looking to stretch and grow your career our culture will embrace you. Open up opportunities with HPE. Job Description: What the Project Is About Data centres are becoming some of Europe's most consequential and fastest-growing electricity users, yet most still appear to the grid as large, opaque, and largely grid-agnostic loads. AIRCAS, short for AI-driven Resource & Cooling forCASting and control for data centres , gives you the opportunity to change this through advanced AI control in a live data-centre environment. You will help build a digital twin, forecasting, and safety-constrained control system that coordinates electricity demand, cooling, heat recovery, and water use. At HPE Labs Ireland, the role will involve live telemetry processing, research, training, evaluation, and deployment of reinforcement-learning controllers across two MODPODs in the Customer Innovation Centre (CIC) data centre. You will validate control policies through replay, hardware-in-the-loop, shadow-mode, and controlled live trials. This is an applied research role spanning physical-system modelling, software engineering, machine learning, and operational deployment. You will collaborate with our international project partners: the University of Porto, CNRS, Savery Tech, RWTH Aachen, Swerim, TerraBarrier, and Daikin Applied. The Opportunity Hewlett Packard Labs is seeking a highly qualified, self-motivated machine-learning and AI researcher to join its growing AI research team in Ireland. The role will accelerate research on digital twins that incorporate machine learning, with a focus on the AIRCAS programme. You will develop and deploy advanced reinforcement-learning control for a live data-centre environment. The work spans research, software engineering, and experimental validation: from data collection and physical-system modelling through forecasting, control-policy training, hardware-in-the-loop testing, shadow operation, and bounded live trials. What You Will Do • Build the CIC data and workload pipeline, including controlled workload generation, telemetry ingestion, time-series data management, data-quality checks, and baseline datasets. • Develop modular digital-twin software that combines site telemetry with physical models, empirical performance maps, cooling and storage models, and operational constraints. • Develop probabilistic forecasts for IT load, cooling demand, and relevant water and heat signals using CIC operational data. • Research, implement, train, and evaluate objective-shifting multi-objective reinforcement-learning policies that balance flexibility, cost, carbon, water use, and durability within hard safety limits. • Implement a price-response interface that produces feasible, auditable flexibility commitments with uncertainty information. • Validate the control stack through replay, hardware-in-the-loop testing, shadow mode, and controlled actuation windows on the CIC MODPODs. • Produce reproducible evidence for flexibility, reliability, sustainabili