Apply on Employer Site

Breakout Ventures · 7 hours ago

Computational Biologist

San Francisco, CA

Contract

Onsite

Mid Level

Breakout Ventures is focused on building a future powered by science, and they are seeking a Computational Biologist at Parallel Bio. The role involves accelerating scientific insights from population-scale immune organoid data through modeling, analysis, and collaboration with scientists and engineers.

Advanced MaterialsEnergyFinancial ServicesLife ScienceVenture Capital

Responsibilities

Modeling & Methods Development Invent and adapt modeling approaches for immune organoid data - donor-aware inference, hierarchical models, robustness to batch and assay drift, uncertainty quantification in order to answer biological questions that matter. Learn and evaluate shared representations across assays, donors, and perturbations to enable transfer to new experimental regimes

Immune Profiling & Multi-Omics Analysis Own analysis for immune phenotyping across flow cytometry, CyTOF, single-cell RNA-seq, CITE-seq, and multiplex functional readouts. Characterize response signatures, quantify donor-to-donor variability and batch effects, and identify what changes under perturbation. Integrate transcriptomic, proteomic, and functional data to support target identification and biomarker discovery

Experimental Design & Scientific Partnership Guide experiments with quantitative thinking: propose designs and follow-ups that disambiguate hypotheses and reduce uncertainty efficiently. Partner with scientists to translate biological questions into computational workflows. Establish statistical best practices for exploratory vs. confirmatory analysis, multiple testing, and sensitivity analyses

Data Quality & Infrastructure Own the integrity of analytical datasets. Develop data quality standards, validation checks, and consistent annotation practices across experiments, donors, and timepoints. Build prototypes that scale socially: reusable analyses, gold-standard reference outputs, and clear definitions so others can trust and extend your work. Partner with Software/Data Engineering to transition validated pipelines into production

Communication & Visualization Generate clear, publication-quality visualizations. Explain assumptions, limitations, and implications to scientists, engineers, and leadership. Document methods and contribute to reports, presentations, and manuscripts

Qualification

Immunology knowledgeHigh-dimensional biological data analysisPython proficiencyStatistical modelingR proficiencyBayesian modelingCloud computingCommunication skillsTeam collaborationProblem-solving

Required

Strong quantitative foundation (statistics, applied math, CS, engineering, or equivalent) and a track record of solving ambiguous modeling and data analysis problems

Experience analyzing high-dimensional biological data (single-cell, cytometry, proteomics, functional assays, or similar)

Immunology knowledge through formal training or hands-on research - you understand what biological questions matter and what the data represents

Proficiency in Python and/or R for rapid, readable prototyping, with version control as standard practice

Ability to translate across disciplines and drive work to completion in a fast-moving environment

Preferred

Bayesian/hierarchical modeling, causal inference, mechanistic-statistical hybrids, or ML approaches for biological data

Experience with organoid systems or primary human tissue models

Experience partnering with engineers to productionize data products (data contracts, validation checks, reference datasets)

Track record training and stress-testing models on large biological datasets, with attention to generalization, robustness to distribution shift, and reusable representations

Familiarity with cloud/cluster computing for scaling analyses