Experience
My experience spans both industry and customer-facing environments, giving me a well-rounded foundation in technical problem-solving and interpersonal skills. During my placement year at Shell, I worked as a Data Scientist within the E-Mobility team, applying machine learning, data analysis, and software engineering to real-world energy and transport challenges. Prior to that, my time at Screwfix developed my communication, teamwork, and ability to perform under pressure - skills that continue to complement my technical work.
| Role | Company | Location | Timeframe |
| Data Scientist | Shell | London | 08/2025 - 09/2026 |
| Retail Assistant | Screwfix | Gerrards Cross, Hayes, Bath | 08/2021 - 05/2025 |
Data Scientist —– Shell
08/2025 - 09/2026 —– London
My placement year as a Data Scientist within Shell's E-Mobility team in central London was an incredibly varied and rewarding experience, spanning data analysis, machine learning, and software engineering to support both research and development and strategic business decisions.
| Data Analysis and Data Engineering | A significant part of my role was hands-on data science and data engineering. Working in Databricks every day, I conducted analysis across hundreds of millions of rows of EV charging data spanning Europe, Asia, and North America - pulling and querying data using SQL before working with it in notebooks. Through the sheer volume and complexity of this work I developed strong proficiency in Apache Spark, learning to write efficient, optimised transformations that made the best use of distributed computing resources, as well as significantly improving my skills in pandas. A core part of this was producing clear, informative, and intuitive graphs and insights that could be understood by both technical and non-technical audiences, and translating findings into reports and presentations tailored for colleagues and senior stakeholders alike. Alongside analysis, I carried out substantial data cleaning and engineering work, building reliable pipelines to prepare and structure raw data into formats suitable for analysis and modelling - pipelines that were then used by other members of the team. Working so closely with this data every day also meant I developed a strong domain knowledge of EV charging and surrounding topics. I believe this is a hallmark of a strong data scientist: having the technical skills is necessary, but so is the willingness to immerse yourself in the domain, understand its nuances, and have the humility to recognise what you don't yet know - and then to go and learn it. |
| Machine Learning and Modelling | I built time series classification algorithms to identify similar charging patterns, and worked as part of a team building upon and improving a Temporal Fusion Transformer model to predict EV charging curves across a wide range of applications - from enhancing the user charging experience to dynamic load management across thousands of Shell Recharge sites. This work builds upon this paper led by my technical supervisor Robert Doel in collaboration with Imperial College London. Beyond curve prediction, I developed forecasting models for power (kW) trends to drive strategic procurement. Also by combining historical voltage (V) data with predicted power profiles, I modelled potential current (A) behaviors to inform the selection of specific cabling and charger hardware. This involved implementing advanced ML techniques to ensure long-term asset viability. I worked closely with the business team to translate these technical insights into NPV and rNPV projections. By ensuring our infrastructure decisions were backed by predictive data, I helped safeguard the profitability of high-cap investments over a 10-year horizon, balancing immediate charging efficiency with long-term financial stability. I also conducted large-scale data analyses on customer charging data, built personalised lightweight machine learning models tailored to individual charging behaviour, and carried out analysis to support rNPV calculations for potential earnings projections. This extended to analysing how such models could be deployed to optimise charging efficiency, reduce energy losses, and enable faster charging for customers. |
| Software Engineering | On the software engineering side, I created, improved, and maintained a suite of internal tools and applications used across the E-Mobility team, built with Python and Plotly Dash, deployed to production and managed through GitHub with CI/CD pipelines via GitHub Actions. Working within an agile framework, I maintained constant communication with business stakeholders to ensure deliverables aligned with evolving requirements, iterating rapidly based on feedback. I also mirgrated the tooling suite from Plotly v4 to v5. Alongside this, I developed a customer-facing lead generation tool targeting fleet operators, with a strong emphasis on intuitive user experience as well as security. Throughout, I gained strong hands-on experience with GitHub in a professional setting, working across development and production environments with structured branching, code review, and automated deployment workflows. |
| Research and Collaboration | I also had the privilege of collaborating with researchers at Imperial College London and Leiden University on several E-Mobility projects, including analysing long-term customer behaviour, investigating battery degradation, and exploring reinforcement learning applications at Recharge sites - working closely with reinforcement learning and mathematics researchers within Shell on the latter - bridging the gap between academic research and real-world industry problems. |
Retail Assistant —– Screwfix
08/2021 - 05/2025 —– Gerrards Cross, Hayes, Bath
My experience at Screwfix across three locations over nearly four years built the interpersonal and operational skills that underpin everything else I do. Working in a fast-paced retail environment taught me how to communicate clearly, perform under pressure, and work as part of a team - qualities I continue to draw on in technical settings.
| Customer Facing | Working at Screwfix in multiple locations gave me a strong foundation in customer service, communication, and teamwork. I thrived in a fast-paced retail environment, consistently approaching every customer interaction with a positive attitude and turning enquiries into sales. I identified high-spending customers, built genuine relationships with them, and promoted them to trade accounts where it was a good fit - directly contributing to increased store revenue. I took pride in going above and beyond for customers, frequently taking extra time to ensure people found exactly what they needed. This dedication was reflected in the feedback I received, including multiple five-star reviews on Google and Trustpilot, as well as many positive responses through online post-order prompted feedback. |
| Warehouse and Operations | Beyond customer-facing work, I played an active role in keeping the store running smoothly. This included accepting and processing deliveries, restocking the warehouse, and maintaining the store to a consistently high standard. I developed strong teamwork and leadership skills, working closely with colleagues to meet weekly sales targets and effectively promote current deals and promotions to customers. Dealing with challenging or high-pressure situations calmly and professionally became second nature over time. |