The company runs cell-free DNA testing for oncology, women's health and organ health, with the aim of making personalized genetic testing part of standard care.
The Data Science research team is hiring a Staff Machine Learning Scientist to help design and prototype new algorithms for genetic and clinical data, run analyses, contribute to patents, and work with R&D and product teams on requirements and product improvements.
The team is made up of statisticians, geneticists, physicians, lab scientists, business staff and software engineers, and the company is growing quickly.
Participation in patents and publications is possible where appropriate.
Responsibilities
Lead research on machine learning and deep learning models built on NGS data: frame problems, pick approaches, and decide when a model earns more investment.
Set the technical direction of your own work as an individual contributor at Staff level, rather than executing someone else's plan.
Design, build and benchmark the models and features for the next Women's Health and Organ Health products, using statistical and deep learning on high-dimensional, noisy, often small sequencing datasets. Choose the simpler method when it is the better fit.
Run, change and interpret existing sequencing pipelines yourself. When results look wrong, trace each processing step to find whether the cause is the pipeline, the data or the biology, and build or extend pipeline components when a project requires it.
Work with molecular biology and assay development scientists on experiment design: what data to collect, how much, and which controls. Help troubleshoot experiments and separate biology problems from data or analysis problems.
Set the team's standard for careful analysis, including sound validation, honest performance estimates, no leakage between training and evaluation data, and clear technical and design documentation.
Contribute to the company's IP portfolio through invention disclosures and patent work, and to its scientific reputation through publications and presentations where suitable.
Mentor data scientists and bioinformaticians, review their work, and serve as the go-to person for hard modeling questions. Make method decisions with minimal direction, including on ambiguous problems, and escalate when needed.
AI tools such as coding agents are used routinely for implementation, analysis and review. You are responsible for everything you ship, regardless of the tool that produced it. Prior experience with these tools is not required; tooling and ramp time are provided.
Requirements
An M.S. or Ph.D. in a quantitative field such as Computer Science, Applied Mathematics, Statistics, Bioinformatics, Computational Biology, Engineering or similar. Equivalent depth gained through work counts fully.
6+ years of hands-on machine learning and data analysis on biological or genomic data after your degree, counting relevant work from the point it became substantially independent, however you reached that point.
A record of models or algorithms you led that reached real use, such as a product, a production pipeline or a decision others relied on, not just a result.
The team is hiring for depth in NGS, bioinformatics and machine learning, and the domain ramp will be provided.
Depth in NGS data analysis, including sequencing QC, alignment and quantification, normalization and their artifacts, with the judgment to catch a wrong result early.
Working fluency with NGS pipelines: running them independently, reading their code and logs, tracing results back through each step, diagnosing failures, and modifying components when needed.
Extensive practical experience with machine learning, deep learning and statistics, including validation and performance estimation on limited or imbalanced data.
Advanced Python, including open-source ML libraries such as scikit-learn, PyTorch, TensorFlow and XGBoost, used in a cloud environment.
Experience processing large datasets and querying with SQL or a similar language.
A proven ability to apply mathematical and statistical principles to real estimation problems and turn them into practical solutions.
Familiarity with assay development and analysis pipelines for molecular or clinical biomarkers.
Ability to explain technical results clearly to non-specialists and a record of delivering complex projects with cross-functional teams.
Preferred: experience with RNA-seq and small RNA/miRNA.
Preferred: experience building probabilistic models for NGS and omics data.
Preferred: experience with diagnostic product development in a regulated or CLIA/CAP setting.
Preferred: experience with Nextflow, WDL or Snakemake and Docker, enough to read, debug and extend workflows.
Preferred: AWS or GCP for large-scale ML training and inference.
Preferred: patents, peer-reviewed publications or conference presentations.
Preferred: a desire to work in a fast-paced environment where a small team has high impact.
Conditions
Base pay range: $170,600 to $213,300 USD. This is a good-faith estimate of the base pay expected at hire, and the final figure depends on experience, qualifications and internal equity.
Equal opportunity policy applies.
Role is eligible for additional compensation through the Total Rewards program.
Benefits
Annual performance incentive bonus.
Long-term equity awards.
Medical, dental and vision health benefits.
401(k) with company match.
Generous paid time off and company holidays.
Additional wellness and work-life benefits.
Life and disability plans for eligible employees and dependents.
Free testing and fertility care benefits for employees and immediate family.