Senior Computational Biologist

present of AI; San Francisco (CA); Remote; USD 150,000 - 210,000; Full time

Job summary

present of AI in San Francisco is seeking a Senior Operations scientist to own the genetic data pipeline from QC through causal target hypotheses. You will shape analyses and automate workflows in a fast-moving AI-driven environment.

The role requires a PhD in statistical genetics with several years of postdoctoral experience, strong Python and Snakemake skills, and a track record in rare variant burden analysis and ML data preparation. Remote work is possible.

Qualifications

• PhD in statistical genetics or a closely related field.
• Hands-on experience with statistical genetics analyses.
• Strong Python and Snakemake workflow skills.
• Experience automating data processing pipelines.

Responsibilities

• Own the genetic data pipeline from QC to causal target hypotheses.
• Run power analyses to guide phenotypes and data types.
• Validate pipelines by recovering known gene-to-phenotype links using public resources.
• Collaborate with ML researchers to prepare multi-omics data for models.

Skills

Statistical genetics

Python

ML data preparation

Power analysis

Education

PhD in Statistical Genetics

Postdoctoral experience

Tools

Snakemake

Job description

Operations · San Francisco · Remote · FullTime · Senior level

The role owns the genetic data pipeline from quality control through to causal target hypotheses, so a strong candidate brings hands on statistical genetics work plus the ability to automate and improve existing workflows. It also calls for running power analyses to guide which phenotypes and data types the company collects, and for proving the pipelines recover known gene to phenotype links against public resources. A PhD with several years of post doctoral experience and solid Python and workflow tooling round out the picture.

How it fits the AI era

Machine learning is already part of how the company finds undiagnosed patients, and this role feeds clean, well prepared multi modal data to those models while judging their results. The judgment about which associations are real, which targets are worth pursuing, and how to design validation stays with the biologist. AI speeds up processing and pattern finding, but causal reasoning and experimental direction remain human work.

How it builds AI experience

The role offers direct exposure to preparing genetic and multi omics data for machine learning models and to shared evaluation with ML researchers, which builds practical fluency in applying AI to disease genetics. A candidate can strengthen this by getting comfortable with how model outputs are validated and by learning the public genomic resources the team relies on. Experience with disease enriched cohorts or target discovery would add to that foundation.

Worth showing

• Statistical genetics PhD
• Python and Snakemake pipelines
• Rare variant burden analysis
• ML data preparation

This is our own read, written from the employer's posting and the company's Spotlight. The employer's posting is the source of truth for the role.

About Probably Genetic

A rare genetic disease platform that uses AI to find undiagnosed patients, offers them genetic testing, and builds a patient-consented dataset for research.