Data & AI Engineer · Leeds, UK
Data pipelines, machine-learning workflows and applied AI—designed around measurable outcomes, reproducibility and production constraints.
Based in Leeds, with 6+ years across banking, consulting, software and applied NLP. Open to Data Engineering, ML Engineering and applied AI roles.
Selected work
Each project starts with a concrete problem, makes the technical decisions visible and links to the underlying work.
Data engineering · Multilingual NLP
A traceable pipeline that transforms noisy multilingual source data into aligned corpora across Catalan, English, French, Italian and Spanish.
Cut a core workflow from 48 to 6 hours and released the resulting corpus as an open, reproducible data product.
Applied ML · Model risk
A leakage-aware temporal modelling pipeline for prescription refill risk, with calibration and explicit analysis of dataset shift.
Surfaced a material performance drop on the later test period—evidence that the model should not be deployed without addressing temporal shift.
Forecasting · Decision science
A simulation-based, out-of-sample comparison of statistical, structural and machine-learning approaches to foreign-exchange forecasting.
Found that random walks remained difficult to beat at short horizons, while structural hybrids improved longer-horizon forecasts for selected currency pairs.
How I work
I combine engineering discipline, statistical thinking and clear communication across the full lifecycle.
Designing traceable, maintainable pipelines across batch processing, distributed compute and cloud workflows.
Python · SQL · PySpark · Hadoop · Airflow · AWSTurning ambiguous problems into measurable experiments, careful validation and systems that support real decisions.
Scikit-learn · XGBoost · TensorFlow · MLflowBuilding multilingual corpora, retrieval workflows and language systems with reproducibility and evaluation in mind.
Transformers · RAG · LangGraph · Semantic searchExperience
Banking, consulting, software and applied AI—connected by a focus on dependable systems and useful decisions.
2024
BBVA · Corporate & Investment Banking
Built PySpark and Hadoop pipelines orchestrated with AWS Step Functions, cutting processing latency by 50%, and integrated XGBoost classification through REST APIs.
2022 — 2024
INDRA
Developed Python and SQL feature-engineering and ETL pipelines for late-payment and fraud modelling, translating model outputs into decision-ready KPIs.
2026 — present
University of Leeds
Build and optimise distributed NLP pipelines on enterprise Linux and NVIDIA GPU infrastructure, cutting a core multilingual workflow from 48 to 6 hours and releasing an open five-language data product.
Beyond the code
From mechatronics and product-building in Peru to financial data systems and applied AI in Leeds.
Read my story