Lead Data Scientist Energy Domain positions focus on delivering results in their domain. This page aggregates open Lead Data Scientist Energy Domain roles and what employers typically expect.
Lead Data Scientist – Energy Domain Location: London (Hybrid) | Practice Area: Data & Analytics | Type: Permanent Build the models powering the future of energy system planning. The Role Capco is seeking a Lead Data Scientist to drive the development of core analytical models within the energy sector. This is a hands-on technical leadership role, combining deep expertise in machine learning and time series modelling with the ability to lead teams, shape technical direction and deliver complex data science initiatives from concept through to production. You will be responsible for leading the design, development and optimisation of advanced statistical and machine learning models that support energy planning, forecasting and strategic decision-making. Alongside technical delivery, you will manage stakeholder relationships, guide cross-functional teams across data, engineering and business domains, mentor junior data scientists, and ensure projects are delivered to a high standard using modern software engineering and MLOps practices. This role is ideal for someone who enjoys balancing hands-on model development with technical leadership, project delivery and helping others grow. You'll also embrace approved AI-enabled ways of working to enhance productivity, accelerate insight generation and improve delivery quality, while applying sound human judgement, responsible AI principles and appropriate governance throughout the model lifecycle. What You'll Do Utilise Python for advanced data analysis, exploration, feature engineering and data processing to uncover insights, trends and patterns, leveraging approved AI tools where appropriate to accelerate analysis and improve efficiency while maintaining rigorous validation and review. Develop and implement statistical models, machine learning models and algorithms, with a particular focus on time series modelling and forecasting, supporting robust, scalable and explainable solutions for complex energy challenges. Lead model development using Azure ML, Databricks and modern MLOps practices, ensuring effective deployment, monitoring, governance and lifecycle management, with appropriate auditability, human oversight and responsible AI guardrails. Collaborate with stakeholders and cross-functional teams to translate business challenges into practical, data-driven solutions while mentoring colleagues, conducting code reviews and promoting engineering excellence and knowledge sharing. Stay current with advances in data science, cloud technologies and AI, including Generative AI and Agentic AI where appropriate, identifying opportunities to improve ways of working and deliver greater value for clients. What We're Looking For Strong hands-on experience in Python, machine learning, statistical modelling and advanced time series forecasting within enterprise-scale environments. Proven experience delivering production-grade analytical solutions using Azure ML, Git, Databricks, MLOps and modern software engineering practices. Strong stakeholder management, leadership and communication skills, with experience mentoring teams and translating complex analytical outputs for both technical and non-technical audiences. Excellent understanding of model validation, feature engineering, explainability, data quality and governance, along with an appreciation of responsible AI practices, human-in-the-loop decision making and appropriate AI controls. A curious mindset with a willingness to adopt approved AI-enabled workflows and automation to improve quality, productivity and delivery outcomes while maintaining professional judgement and accountability. Bonus Points For Experience working with geospatial data and spatial analytics. Experience with AI, including Generative AI and Agentic AI, applied within enterprise environments. Experience with energy system modelling, grid analytics, demand forecasting or energy market data. Familiarity with distributed computing, Spark, PySpark or cloud-native data plat…