Data & Systems Engineer · Quantitative Finance · Builder
Computer Engineering graduate currently creating production data systems and enterprise analytics solutions at MTR Corporation. I have a deep interest in quantitative finance, machine learning, and the usage of software to turn complex ideas into tangible solutions. In my free time, I am an avid language learner and enjoy hiking and rowing. Feel free to reach out at: josespignou@gmail.com
Built 15+ Azure Data Factory pipelines and engineered Databricks solutions for marketing automation. Delivered a Solace→Databricks real-time streaming pipeline, migrated Power BI reports to programmatic Python reporting, and standardised enterprise architecture documentation across the Data&EA department. Azure Databricks Data Engineering ETL
Developed and presented ML workshops for HKU students. Prototyped Computer Vision and NLP models for research and industry, and engineered a multimodal RAG pipeline benchmarking LLMs, OCR, and layout detection for grounded document retrieval. NLP CV ML RAG
Curated highlights — View all → Continuous Learning
Five-course Wharton specialization in quantitative modeling, spreadsheets, risk, scenarios, and capstone.
Four-course specialization covering modeling, spreadsheets, financial acumen, and corporate finance.
Four-course specialization on equities, forex, bonds, and derivatives across capital markets.
Yale course on securities, insurance, banking, and regulation through behavioural finance.
DeepLearning.AI specialization covering supervised learning, unsupervised learning, and recommender systems.
Six-course professional certificate on Python for data science, web development, and automation.
Johns Hopkins specialization on neural network theory, advanced architectures, and AI ethics.
IBM course introducing the most commonly used data science tools and workflows.
Rotation within Data&EA Department: Engineered Databricks solutions and built 15+ Azure Data Factory pipelines supporting marketing automation delivery. Migrated Power BI reports to Databricks using Python-based, programmatic reporting with stakeholder validation. Delivered a Solace→Databricks real-time streaming solution while running twice‑monthly IT governance meetings, standardising EA documentation, and automating process-efficiency dashboards (Power BI/Excel VBA). Azure ETL AnalyticsData Engineering Governance
Developed and presented workshops on Machine Learning targeted towards HKU students. Prototyped and implemented Computer Vision and NLP models for both research and industry purposes. Engineered a multimodal RAG pipeline, benchmarking LLMs, OCR, and layout detection to enable accurate retrieval and grounded responses from complex documents. NLP CV ML
Implemented Computer Vision algorithms on a cloud production environment, constructed and enhanced inference pipelines, assisted in CV and NLP research, developed tools to build a systematic research and testing pipeline. NLP CV ML
Say hello at josespignou@gmail.com.
