Origin

I spent four years at the bench doing molecular biology — cloning, cell culture, assay development — before realizing that the data coming out of those experiments was often more interesting than the experiments themselves. That curiosity pulled me toward computation, and eventually to an MS in Data Science at UC Berkeley, where I learned to build the systems that turn messy biological data into reproducible evidence.

The bench background isn’t a detour. It’s the reason I can read a study design, spot a cohort definition problem, or push back on a survival model assumption in ways that a pure software engineer can’t.

What I Build

  • End-to-end data pipelines from raw EHR and claims tables to analysis-ready cohorts using Snowflake, dbt, and Python
  • Real-world evidence (RWE) studies — propensity score matching, survival analysis, Cox proportional hazards, and causal inference
  • ML models on clinical and biomedical datasets with SHAP-based interpretability for clinical stakeholders
  • Data products that connect translational scientists with the infrastructure they need to ask better questions faster

What I’m Looking For

I’m targeting senior data science and clinical data engineering roles at biopharma, CRO, or health tech companies where I can work at the intersection of clinical development and data infrastructure — designing RWE studies, building patient cohort pipelines, and modeling treatment outcomes at scale. The right role gives me hard problems, clinical domain exposure, and a team that cares about getting the science right, not just shipping dashboards.

nicklee0101@gmail.com LinkedIn GitHub