Seon Min Kim

For recruiters

Four years in drug regulatory affairs taught me to ask what evidence a claim needs. Now I build health AI and data pipelines with that question designed in.

  • LocationSan Francisco Bay Area
  • Work authorizationAuthorized to work in the U.S.
  • Looking forOpen to roles in the US, Singapore and Korea
  • LanguagesKorean and English (fluent)

    • Two tracks

    Pick the one closest to your role.

    Applied AI / ML

    Applied AI, AI/ML engineer, AI scientist in health and bio

    Building LLM and ML systems, deciding what the model may and may not decide, and testing whether results hold up.

    1. Rare Disease Phenotype Agent
    2. Prompt2Pump (1st place, Track 5)
    3. SourceLock
    Download résumé PDF

    Health Data Science & Bioinformatics

    Health data scientist, bioinformatics scientist, computational biology

    Cleaning large raw datasets end to end, integrating multi-omics data, and drawing statistically sound conclusions.

    1. Kidney transplant multi-omics
    2. GLP1-Sentinel
    3. Scleroderma lung disease scRNA-seq
    Download résumé PDF

    How I work

    In every system I build, I first decide which parts a model is allowed to decide and which parts must come from rules or curated data. In the Rare Disease Phenotype Agent, the language model only translates notes into standard terms. In SourceLock, deterministic rules keep final authority over approval status and prohibited claims. I learned this habit in regulatory affairs, where every claim needs evidence someone else can check.

    한국어 이력서 PDF AI-readable summary TXT

    Let’s talk.

    The fastest way to reach me is LinkedIn.

    Message on LinkedIn GitHub