John Lewis Partnership, London
Since March 2025
• Delivered £2M business benefit through replenishment safety stock optimisation, increasing product availability while reducing overstocking. Led large-scale trial. Built supply chain simulation & demand forecasting models, integrated into replenishment workflows. Partnered with supply chain, operations, and commercial teams
• £500k potential annual business value via forecasting distribution centre outbound stock using hierarchical intermittent time series models, across 2k product categories and 3 distribution centres
• Delivered first-in-business Click & Collect location optimisation, combining data science and OR techniques, boosting stakeholder productivity with scalable, low-latency solution with Streamlit frontend
• Developed automated, data-driven reverse logistics disposition optimisation solution, maximising returned/repaired product profit recovery and boosting operational efficiency at distribution centres
• Developed Initial Buys tool suite for product launch, assisting Commercial teams to automate similar product search via embedding and attribute matching, forecast new product initial sales and recommend order volume; data-driven approach to reduce guess work, risk of overstocking or missed sales
• Enabled stakeholder adoption of data-driven decision-making, translating analytical insights into operational strategies through structured storytelling
• Led DS product scoping, solution design, and roadmap ownership, partnering with stakeholders to ensure measurable business value delivery, working with data owners to ensure robust data quality
• Established best practices across DS team, standardising solution architecture patterns and leading technical knowledge-sharing sessions
• Led DS mentorship and capability development
OctaiPipe (t-dab.ai), London E1
April 2022 - March 2025
• Main contributor to 7 commercial & industrial ML projects (incl. 2 Innovate UK), delivering edge ML solutions for fault detection, HSE compliance, and risk modelling
• Lead DS contributor to reinforcement learning in company pivot to data centre energy optimisation
• Designed and deployed RAG/LLM infrastructure (LlamaIndex, FastAPI, Kubernetes, Weaviate)
• Integral part of product team delivering first version of company’s main edge-IoT ML platform, QA testing. Productised state-of-the-art ML algorithms and trustworthy AI features
• Delivered data insights to customers; authored white papers and company blog posts. Led customer onboarding, created product demo videos. Project scoping
Department of Physics and Astronomy
The University of Kentucky
August 2021-February 2022
New York University
Thesis Adviser: Professor Massimo Porrati
2021
The Hong Kong University of Science and Technology
First-Class Honours
2014
Core:
Python, SQL, Git, Linux
Data Pipelines:
Snowflake, dbt, PySpark, InfluxDB
Optimisation & Simulation:
Supply chain optimisation, simulation modelling, reinforcement learning
OR-Tools, Gymnasium, stable-baselines3
Machine Learning, Forecasting, Causal Inference, Recommendation Systems:
Supervised & unsupervised learning, time series forecasting, anomaly detection, explainability, model auditability. Causal inference, A/B test. Recommendation systems.
Hierarchical Bayesian models (NumPyro), intermittent demand forecasting, multi-time-series modelling, recursive ML forecasting (XGBoost / skforecast), ALS, XGBRanker
Pandas, NumPy, SciPy, Scikit-Learn, TensorFlow, PyTorch, Transformers, XGBoost, SHAP
LLMs & AI:
Google Agent Development Kit, Github Co-pilot, NotebookLM, LlamaIndex
MLOps & Production ML:
CI/CD, ML pipelines, model monitoring, solution architecture design
Vertex AI Pipelines, GCP, Docker, Kubernetes, Azure
Visualisation & Analytics:
Storytelling & insight communication
Streamlit, Tableau, Grafana, Matplotlib, Plotly
Leadership:
Stakeholder engagement, mentoring, product roadmap ownership
Value-driven problem framing, data-driven decision enablement, Agile
Domain:
Retail & large-scale supply chain optimisation, industrial ML use cases, violin making
A full list of my publications in physics is available at