Senior Computational Biologist

ABOUT PROBABLY GENETIC

Probably Genetic is changing the lives of patients living with severe, complex diseases. Our data platform is used by drug developers and patient advocacy groups to develop and launch treatments for these patients. Our technology discovers undiagnosed patients online, analyzes their disease state using machine learning and at-home testing, and enables compliant communication with patients. In doing so, we help patients access diagnoses, clinical trials, and treatments as early as possible.

We are a tight-knit group of hard-working, ambitious problem solvers united by a mission greater than ourselves. We do well by doing right by patients. We are developing some of the most cutting-edge solutions in healthcare, and our roadmap is packed with innovations in bioinformatics, AI, and drug development. We have built a lean, all-star team to help us bring our vision to life, and we want you to be a part of it.

Probably Genetic has raised multiple rounds of funding from Silicon Valley’s best investors, including Threshold, Khosla, and Y Combinator, and offer competitive salaries, comprehensive benefits, and meaningful early stage equity.

ABOUT THE ROLE:

Probably Genetic has built one of the deepest phenotyped genetic disease cohorts in the U.S. by facilitating patients' access to genetic testing. We are now using this rich database for target discovery.

We're hiring a Senior Computational Biologist to own our bio data pipelines and interpretation end-to-end. . You'll take our data from QC through positive control recovery to novel, causal, direction-of-effect target hypotheses, and collaborate closely with our team on prioritizing new data modalities to collect.. In addition, your results will be used by our ML researchers to train ML models on multi-modal data and support target discovery. . This is a hands-on, first-of-its-kind role reporting to our VP of R&D.

WHAT YOU'LL DO:

- Bio data processing and QC: take over, improve and fully automate our in-house pipeline for genetic data analysis

- Run power analyses and use your insights to inform which phenotypes and indications we prioritize, how we scale our database, and which data modalities we collect

- Prove our data and pipelines recover known gene-phenotype associations and approved target-indication pairs, and replicate them against public resources

- Conduct association and causal gene mapping in a selected indication, incl. via rare variant burden tests, colocalization tests, and Mendelian randomization

- Partner with ML researchers on data preparation, multi-modal integration and shared evaluation

- Hand off prioritized targets to wet lab validation and inform in vitro experimental plans and priorities

WHO YOU ARE:

- PhD in statistical genetics, computational biology, bioinformatics, or similar, plus 4+ years post-PhD in academia or industry

- Proven track record (via shareable projects or publications) of hands-on experience in processing, analysing and interpreting genetic / genomic data; Working knowledge of public human genetic and functional genomics resources (e.g. gnomAD, GTEx, Open Targets, ClinVar)

- Strong Python skills; experience with workflow managers (e.g., Snakemake) and comfortable working with cloud-scale genomic data resources

- Enough ML fluency to collaborate closely, support data preparation and have productive discussions

- Energized by our mission: develop new treatments for patients who have none

- Bonus: target discovery or human genetics experience in biotech or biopharma; experience with genetic disease and/or disease-enriched cohorts; multi-omics (e.g., transcriptomics, proteomics)

AS WITH ALL NEW HIRES AT PROBABLY GENETIC, YOU WILL ALSO NEED TO BE:

- A good person. We work with some of the most marginalized populations on the planet and empathy is key

- Patient-focused and motivated to have a lasting, positive impact on humanity

- Comfortable in a fast-paced, oft