Staff Scientist, Machine Learning (Genomics)

Natera•San Carlos, CA

17h•$170,600 - $213,300

About The Position

Natera is seeking a highly motivated Staff Machine Learning Scientist for its Data Science research team. The role involves designing and prototyping algorithms for genetic and clinical data, conducting data analysis, developing models, contributing to intellectual property, and collaborating with R&D and product teams to define requirements and improve products and processes. This is an individual-contributor role with Staff-level scope. The scientist will lead research and set technical direction for machine learning and deep learning work using next-generation sequencing (NGS) data; develop and benchmark models and features for Women Health and Organ Health products; and work directly with sequencing pipelines to interpret outputs, diagnose issues, and build or extend components when needed. The role also partners with molecular biology and assay development scientists on experimental design and troubleshooting. The position establishes rigorous standards for validation, performance estimation, leakage prevention, and documentation. It includes contributing to invention disclosures, patents, publications, and presentations as appropriate; mentoring data scientists and bioinformaticians; and making independent technical decisions. AI tools, including coding agents, are routinely used, with the employee accountable for the work they deliver.

Requirements

M.S. or Ph.D. in a quantitative field such as Computer Science, Applied Mathematics, Statistics, Bioinformatics, Computational Biology, Engineering, or a similar field; equivalent depth developed through work is accepted.
At least 6 years of hands-on machine learning and data analysis experience on biological or genomic data after the degree, with relevant experience counted from when work became substantially independent.
Demonstrated track record of leading models or algorithms that reached practical use in a product, production pipeline, or consequential decision.
Depth in NGS data analysis, including sequencing QC, alignment, quantification, normalization, and sequencing artifacts.
Working fluency with NGS bioinformatics pipelines: independently running them, reading code and logs, tracing results through processing steps, diagnosing failures or unexpected outputs, and building or modifying components when needed.
Extensive practical experience with machine learning, deep learning, and statistics, including model validation and performance estimation on limited or imbalanced data.
Advanced Python skills and experience with open-source machine learning libraries such as scikit-learn, PyTorch, TensorFlow, or XGBoost in a cloud environment.
Experience processing large datasets and using a query language such as SQL.
Ability to apply mathematical and statistical principles to real estimation problems and develop practical solutions.
Familiarity with assay development and analysis pipelines for molecular or clinical biomarkers.
Clear communication of technical results to people with different backgrounds and a record of delivering complex projects with cross-functional teams.

Nice To Haves

Experience with RNA-seq and small RNA/miRNA.
Experience building probabilistic models for NGS and omics data.
Experience with diagnostic product development in a regulated or CLIA/CAP setting.
Experience with workflow orchestration tools such as Nextflow, WDL, or Snakemake, and containerization with Docker, sufficient to read, debug, and extend existing workflows.
Experience using AWS or GCP for large-scale machine learning training and inference.
Patents, peer-reviewed publications, or conference presentations.
Desire to work in a fast-paced environment where a small team has high impact.

Responsibilities

Lead machine learning and deep learning research using NGS data and set technical direction for projects.
Frame modeling problems, select approaches, and determine whether models merit further investment.
Design, build, and benchmark models and features for Women Health and Organ Health products using statistical learning and deep learning.
Analyze high-dimensional, noisy, and often small-sample sequencing data, choosing simpler methods when appropriate.
Run, inspect, and interpret existing sequencing pipelines; trace unexpected results through processing steps and determine whether issues stem from the pipeline, data, or biology.
Build or extend pipeline components when project needs require it.
Partner with molecular biology and assay development scientists to design experiments, select data and controls, and troubleshoot experimental issues.
Establish rigorous analysis practices, including sound validation design, honest performance estimates, prevention of training/evaluation leakage, and documentation.
Support high-quality technical and design documentation.
Contribute to Natera’s intellectual property through invention disclosures and patent work, and to scientific output through publications and presentations where appropriate.
Mentor data scientists and bioinformaticians, review their work, provide modeling guidance, make independent technical decisions, and escalate issues when appropriate.
Use AI tools, including coding agents, responsibly and own the quality of delivered work.
Communicate technical results to non-specialists and deliver complex projects with cross-functional teams.