I am a data scientist and machine learning engineer who applies maths and stats to problems in healthcare. I work mainly in Python and R with occasional forays into SQL via DuckDB.

Applying NLP models (various incarnations of BERT, LLMs and simple rule-based algorithms) to messy clinical data; Data linkage using DuckDB; Cancer risk prediction models; Developing tools that assist data scientists

Python • R • SQL; ML frameworks: PyTorch, Hugging Face; Cloud and ML deployment: Databricks, Pyspark, Azure, RunPod; Dev: VS Code, uv, GitHub, Quarto

Exploring mountains and hiking trails in various parts of the world; Books and documentaries; Riding my bike; Cooking experiments

• Website: https://ajl2718.github.io
• Linkedin: https://www.linkedin.com/in/alex-lee-b120a0163/