Member of Technical Staff: Statistical Genetics
Core
Turn genetic association data into a rigorous substrate for biological foundation models by building statistical genetics resources and evaluating model performance on genetic variation.
Role type
Senior IC statistical genetics scientist (data architect & methods scientist)
Builds
Large-scale statistical genetics resources (GWAS, QTL maps, fine-mapping, variant annotations, population reference panels) and benchmarks for genetic architecture.
Domain
Statistical genetics + AI/ML for genomics
Deliverable
production ML models
Required skills
Statistical genetics methods (GWAS, LD, ancestry, heritability, fine-mapping, QTL, rare variant analysis, polygenic risk), Python/R programming, large genetic resource experience (UK Biobank, All of Us, TOPMed, gnomAD, GTEx, FinnGen, ENCODE), agentic coding tools
Preferred skills
Polygenic risk score development, ML for genomics (sequence models, variant effect predictors, multimodal models), colocalization, Mendelian randomization, TWAS, causal inference, privacy-preserving genomic analysis
Technologies
Python, R, UK Biobank, All of Us, TOPMed, gnomAD, GTEx, FinnGen, ENCODE
Responsibilities
Build and evaluate large-scale statistical genetics resources for model training and assessment; Design benchmarks testing model capture of genetic architecture; Partner with AI/ML engineers to analyze model behavior on variant effect prediction and disease association; Develop practical standards for genetic data provenance, QC, leakage prevention, and responsible use.
Seniority
Senior, hands-on IC