Senior Scientist II, Statistical Genetics

Cytokinetics•South San Francisco, CA

5d•$184,500 - $215,250•Onsite

About The Position

Cytokinetics is seeking a highly motivated statistical geneticist to join its growing team and help discover and evaluate therapeutic targets for diseases involving impaired cardiac and skeletal muscle function. The role leads hands-on research using large human cohorts, sequencing data, and rich phenotypes to connect genetic variation with disease biology and therapeutic opportunities. It requires a strong foundation in statistical genetics, applied AI/ML experience, and an interest in translating genetic insights into clinical applications.

Requirements

Ph.D. in Statistical Genetics, Human Genetics, Bioinformatics, Computational Biology, or a related field.
Four or more years of post-doctoral or industry experience.
Strong expertise analyzing large-scale genomic datasets, including GWAS and sequencing data.
Demonstrated experience translating genetic associations into candidate therapeutic hypotheses or targets.
Experience with multidimensional and longitudinal data analysis in biology or medicine.
Proficiency in R and/or Python, with experience applying and critically evaluating statistical and machine-learning methods.
Track record of independent research, such as first-author publications, methods, or software.
Strong communication skills.

Nice To Haves

Experience with cloud computing platforms such as AWS or Google Cloud and biobank research analysis platforms such as UKB RAP or All of Us Workbench.
Experience with machine-learning and deep-learning methods, and strong interest in applying them to biological problems.
Previous therapeutic-area experience in cardiovascular and neuromuscular disease is strongly desired.
Experience using AI-assisted coding tools in reproducible workflows.

Responsibilities

Perform common- and rare-variant association studies and meta-analyses across biobanks such as UK Biobank, All of Us, and FinnGen to discover and replicate associations across diverse ancestries.
Develop quantitative and longitudinal phenotypes from EHR and imaging data, including cardiac MRI and DEXA, using AI/ML methods to better capture disease biology.
Apply fine-mapping, colocalization, Mendelian randomization, and burden methods—including protein language model-based variant prioritization—to identify causal genes and direction of effect.
Prioritize targets using genetic evidence for efficacy and safety, such as PheWAS, allelic series, and protective variants, and partner with experimental teams on validation.
Build reproducible pipelines on research analysis platforms, and present findings internally, at conferences, and in publications.