Computational / Bioinformatics Scientist
Location: San Diego, CA
Job Type: Full-Time
Salary Range: $174,000 - $185,000
Position Overview
We are building a high-throughput data analysis pipeline from first principles, on a short timeline, with a small team.
This role is the connective tissue between biology and algorithm. You will support chemistry and assay teams with rigorous quantitative analysis, build first-principles simulations that let us study instrument behavior before reliable data exists, and own the downstream data processing stack.
This is not a research position. You will write production-intent code, ship working tools, and own specific technical tracks end-to-end. The team is small, the problems are novel, and the timeline is real.
Why Join Us:
Own the biology-facing analytics track: image-based signal extraction, sequential signal quality analysis, experiment design support, and quantitative troubleshooting for teams
Build first-principles simulations of instrument behavior — signal distributions, optical models, and system dynamics — to study system behavior before reliable instrument data is available
Design and implement the downstream data processing stack: signal diversity handling structured output formats
Characterize data quality across difficult signal patterns and edge cases that stress classification and quality scoring models
Define quantitative metrics and diagnostics to guide chemistry and hardware teams toward theoretically achievable performance limits
Collaborate with the ML engineer on labeled datasets, ground truth construction, and calibration inputs for quality scoring and signal classification model development
Qualifications and Education:
MS and 13+ years or PhD and 10+ years of experiencein computational biology, bioinformatics, engineering, statistics, physics, computer science, or a closely related field; MSc considered with a strong industry track record in product-facing roles
Must demonstrated experience shipping quantitative analysis tools or pipelines in a product development context — you have owned a technical track, shipped something, and moved it from prototype through to use
Must have strong programming skills in Python (numpy, scipy, pandas/polars, scikit-learn) or R (tidyverse, Bioconductor); fluency in both is a plus
Fluent working with multi-modal scientific data: tabular, image, and tensor formats — not just one
Familiarity with high-through put data pipelines and computational biology and bioinformatics methods: biological data analysis, QC metrics, and quantitative modeling
Prior direct experience interfacing with wet lab, chemistry, or assay teams — you know how to translate between biological experiment and quantitative model
Strongly Preferred & Nice To Have:
Experience at a life sciences instrument or measurement technology company.
First-principles mechanistic simulation experience: PDEs, ODEs, stochastic systems, or optical/imaging physics — the ability to build a predictive model from governing equations before empirical data is available is directly useful here
Demonstrated software projects: public GitHub contributions, open-source tools, or comparable evidence of engineering quality and technical ownership
Comfort using AI-assisted development tools to move faster — this team expects everyone to use the best available toolsImage analysis experience: microscopy, spatial data, or feature extraction from 2D/3D image stacks
Experience with combinatorial design problems: code design, edit distance constraints, composition bounds
Familiarity with on-instrument or embedded compute constraints (understanding what "runs in real time on hardware" means in practice)
We are an equal opportunity employer. We thrive on diversity and collaboration.
foresite-labs-fl2024-006