Principal Scientist

Cytokinetics•South San Francisco, CA

21h

About The Position

Cytokinetics is seeking a highly motivated computational scientist to lead translational biomarker discovery at the intersection of human genetics, multi-omics, and AI/ML. The role focuses on identifying biomarkers that diagnose disease, predict disease progression, and anticipate patient outcomes in conditions involving impaired cardiac and skeletal muscle function. By combining genetic evidence, multi-omics profiles, and clinical phenotypes, the scientist will investigate which patients are at risk and the underlying reasons. The position partners closely with experimental biologists and clinical research teams to translate patient-derived insights into discovery and carry discoveries toward clinical application. It is a hands-on computational leadership role applying modern AI/ML to human data in muscle disease. The position is based on a primary location of South San Francisco, California. The expected salary range is stated as $202,5000-$236,250; the posting notes that base pay may vary by geographic region, job-related knowledge, skills, experience, and other factors. The compensation package also includes equity in the form of stock options and/or restricted stock units, comprehensive health, dental, vision, life and disability insurance, 401(k) retirement benefits with employer match, learning and wellness stipends, and paid time off. Benefits may change and vary by jurisdiction.

Requirements

Ph.D. in Computational Biology, Human Genetics, Bioinformatics, or a related field.
At least 6 years of post-doctoral or industry experience.
Strong expertise in analyzing large-scale genomic datasets, including GWAS and sequencing data.
Deep expertise in transcriptomics, proteomics, or single-cell analysis, with integration across data types.
Track record of translating human molecular or phenotypic data into disease mechanisms, therapeutic targets, or biomarker strategies.
Proficiency in R and/or Python.
Expertise in study design, batch effects, confounding, longitudinal data, and evaluation of AI/ML methods.
Strong interest in applying AI tools, including LLMs and agents, to translational research; production experience is not required.
Ability to lead cross-functional projects and mentor scientists.

Nice To Haves

Experience with population biobanks such as UK Biobank or All of Us, or with disease-specific cohorts.
Drug discovery experience, including biomarker analysis, patient sample studies, or patient stratification.
Experience integrating genetic evidence with single-cell or tissue-specific expression data.
Previous therapeutic-area experience in cardiovascular and neuromuscular disease is strongly desired.
Experience prototyping LLM-assisted or agentic workflows.

Responsibilities

Integrate genomic, transcriptomic, proteomic, and single-cell data to trace how genetic variation drives molecular and cellular changes in cardiac and skeletal muscle disease.
Discover and validate diagnostic and prognostic biomarkers of disease onset, progression, and clinical outcomes using omics and longitudinal clinical data from biobanks and patient cohorts.
Develop and validate AI/ML methods that link molecular profiles with imaging and clinical phenotypes to define patient subgroups for precision medicine.
Investigate disease heterogeneity and genotype-phenotype discordance to uncover modifier pathways and generate mechanistic hypotheses for experimental follow-up.
Lead translational applications of LLMs and agents, such as evidence synthesis and data curation, with appropriate benchmarking.
Lead cross-functional projects and mentor scientists.