Peterborough, England, United Kingdom
Data Scientist and Machine Learning Engineer with experience delivering predictive models, analytics solutions, and data pipelines in engineering, finance and research environments. Strong background in time-series, sensor and telemetry data analysis and large-scale data processing. Proven ability to deploy production-ready ML solutions and communicate complex insights to technical and business stakeholders.
• Build and deploy predictive machine learning models for equipment health monitoring, enhancing fault detection and supporting proactive maintenance strategies. • Develop scalable data pipelines and analytics workflows using Python, SQL, and Snowflake to process and analyze large-scale engineering datasets. • Create and deploy interactive dashboards, web applications, and self-service analytics solutions using Streamlit, Power BI, and Tableau. • Conduct time-series analysis, feature engineering to extract actionable insights from high-frequency machine and sensor data. • Partner with engineering teams and leadership to translate complex analytical findings into data-driven business and operational decisions. • Standardize analytics methodologies, documentation, and development practices to improve reproducibility, scalability, and enterprise-wide adoption. • Drive operational efficiency and continuous improvement by transforming raw engineering data into predictive and prescriptive insights.
• Leverage enterprise engineering and business data systems to identify, analyze, and solve complex technical and operational challenges. • Apply multidisciplinary analytical methods to support advanced engineering investigations and drive business intelligence initiatives through data-driven insights. • Develop intuitive reports, dashboards, and visualizations that transform complex datasets into actionable information for stakeholders. • Present analytical methodologies, findings, and recommendations to both technical teams and business leadership, enabling informed decision-making. • Establish and document scalable analytics workflows, processes, and best practices to improve repeatability, knowledge sharing, and analytics adoption across the organization. • Utilize advanced data science, machine learning, and statistical techniques to uncover hidden patterns and create value from large-scale engineering datasets. • Influence the evolution of data infrastructure, analytics capabilities, and technology adoption to strengthen a data-driven engineering culture. • Design, automate, and deploy analytics solutions through web applications, dashboards, and self-service tools that empower engineering teams and improve operational efficiency
• Configured and customized Lasernet document management and output solutions to meet client business and reporting requirements. • Collaborated with clients to gather requirements, deliver system configurations, and support implementation activities. • Performed testing, troubleshooting, and user support to ensure successful solution deployment and adoption. • Developed documentation and provided technical guidance to end users and project stakeholders.
• Developed unsupervised machine learning solutions for human behavior classification using wearable sensor data. • Applied clustering algorithms and time-series analytics to uncover behavioral patterns and generate actionable insights.
• Collaborated with the MRC Epidemiology Unit to collect and analyze large-scale wearable accelerometer data for human activity and behavior research. • Processed high-frequency (100Hz), multi-day time-series sensor data from wrist-worn devices using HDF5-based data pipelines. • Developed machine learning models to estimate activity energy expenditure and classify behaviors such as sleeping, walking, cycling, and driving. • Applied supervised and unsupervised learning techniques, including regression and k-means clustering, to identify behavioral patterns and activity states. • Analyzed UK Biobank and custom-collected datasets to model movement behaviors and derive population-scale health insights. • Leveraged signal processing, feature engineering, and behavioral segmentation methods to infer human activities from multi-dimensional accelerometer data.
• Analyzed diabetes health indicator data to identify key biological and demographic factors associated with diabetes risk. • Applied statistical hypothesis testing (chi-square analysis) to determine significant predictors and assess variable relationships. • Developed logistic regression models to quantify predictor importance and evaluate their influence on diabetes outcomes.