Description

I am a Chartered Engineer (IET, UK) with a PhD in Mathematical Optimisation for Predictive Control from Imperial College London, and over 10 years of cross-functional professional experience delivering high-impact AI, Machine Learning, and data-driven solutions across various industries including Energy Utilities, Pharmaceuticals, Chemicals, and Manufacturing. I have expertise — in both product-focused and consultancy settings — leading the end-to-end machine learning lifecycle, specialising in complex time-series modelling, predictive analytics, supervised/unsupervised learning,

and advanced mathematical optimisation. I am adept at steering cross-functional engineering teams, collaborating with corporate stakeholders to shape product roadmaps, and translating sophisticated systems into scalable, production-grade applications that drive significant commercial value.

Industry field of expertise

Languages

English
Native or bilingual

Workplace preferences

Can work on-site

Warrington (up to 50km)

Carbon Re/Gigaton,
Lead Machine Learning Engineer
April 2026 - Today (3 months)
United Kingdom
Core Focus: Collaborated within a cross-functional engineering team on the end-to-end development and production deployment of machine learning algorithms for industrial process optimisation, targeting energy efficiency in heavy industries. Digital Twins: Engineered high-fidelity process digital twins utilising Bayesian optimisation, establishing robust pipelines to version and deploy serialised model artifacts to an AWS S3 model store for real-time inference.
Predictive Control & Impact: Contributed to the design of multivariable predictive controllers leveraging these digital twins to achieve tight, simultaneous control of critical KPIs; helped minimise precalciner temperature standard deviation, delivering a collective £140,000 reduction in annual
fuel costs.
Machine learning Deep Learning Python Data science Amazon Web Services
Voltaware
Head of Energy Insights
May 2023 - March 2026 (2 years and 10 months)
Team Leadership: Led and managed a cross-functional team of Data Scientists, Data Analysts, and Machine Learning Engineers to enhance and scale Voltaware's AI energy analytics platform.
Stakeholder Management: Interfaced directly with energy utilities to align technical capabilities with business intelligence demands, managing expectations and presenting complex data insights.
Product Architecture: Coordinated the end-to-end architecture and algorithmic enhancements of the energy insights product, processing large volumes of smart meter time-series consumption data.
Business Value: Directed the commercial deployment of the AI insights engine for a major EU energy utility, successfully scaling data-driven personalised insights to 50,000+ energy customers.
Voltaware
Senior Data Scientist
July 2021 - May 2023 (1 year and 10 months)
United Kingdom
Product Development: Designed and fully implemented the first version of the AI energy analytics library to classify and disaggregate major home appliance loads based on raw time-series smart meter electricity profiles.
Technical Execution: Engineered custom preprocessing and feature engineering pipelines that integrated supervised classifiers (XGBoost, Random Forests) with unsupervised learning (GMM, KMeans) to compute high-accuracy, appliance-specific cycle analytics. Coordinated the containerisation and deployment of this python-based analytics engine to AWS cloud.
Key Results: Achieved 85–90% accuracy in appliance detection and cycle classification, providing the baseline algorithmic validation required for subsequent utility rollouts.