Lead Bioinformatics & ML Scientist, Cancer Epigenomics

Natera, Inc.; San Carlos (CA); On-site; USD 172,000 - 214,000; Full time

Benefits offered by this job

Annual bonus

Equity awards

Health benefits

401(k) with company match

Paid time off

Wellness programs

Job summary

Natera, Inc. in California seeks a Lead Bioinformatics & Machine Learning Scientist to advance epigenomics in oncology within our Bioinformatics R&D team.

You will develop ML methods for early cancer detection from cfDNA methylation data and provide technical leadership across projects. The role emphasizes collaboration with molecular biologists, mentoring scientists, and shaping model interpretability and reproducibility.

Qualifications

• PhD in a quantitative field with 4–8+ years post-PhD experience.
• Experience in cancer genomics or epigenomics; cfDNA/methylation data preferred.
• Strong background in statistics and applied ML; deep learning a plus.
• Proven track record of methods for high-throughput sequencing data.
• Strong Python skills and experience with scientific libraries.

Responsibilities

• Drive technical workstreams from problem definition to final classifiers.
• Design and validate ML and statistical methods for cancer diagnostics.
• Promote model interpretability, uncertainty estimation, and reproducibility.
• Develop robust feature pipelines for cfDNA methylation data.
• Collaborate with scientists, mentor team members, and lead reviews.
• Lead code and design reviews and contribute to scientific excellence.

Skills

Machine learning

Statistical analysis

Hypothesis testing

Education

PhD in Bioinformatics/CS/ML

Tools

Python

Git

Nextflow

Snakemake

Linux

Shell scripting

Cloud computing

Job description

Natera, Inc. in California seeks a Lead Bioinformatics & Machine Learning Scientist to advance epigenomics in oncology within our Bioinformatics R&D team.

You will develop ML methods for early cancer detection from cfDNA methylation data and provide technical leadership across projects. The role emphasizes collaboration with molecular biologists, mentoring scientists, and shaping model interpretability and reproducibility.