Lead Bioinformatics & Machine Learning Scientist (Epigenomics)

Natera•San Carlos, CA

About The Position

Natera is seeking a Lead Bioinformatics & Machine Learning Scientist to contribute to research and development in its Bioinformatics Research and Development team, focused on Epigenomics in Oncology. The team develops machine learning methods for early cancer detection using cell-free DNA (cfDNA) methylation data. The successful candidate will develop and expand state-of-the-art machine learning methods for early cancer detection and provide technical leadership and mentorship within a collaborative team. The role involves taking methods from problem definition through delivery of final classifiers to downstream validation teams; designing, implementing, and validating machine learning and statistical methods for cancer diagnostics; and developing feature engineering and extraction pipelines for cfDNA methylation and sequencing data. The scientist will work closely with molecular biologists on experimental design and data quality, establish best practices for interpretability, uncertainty estimation, and reproducibility, and participate in code and design reviews. Natera describes itself as a global leader in cfDNA testing, working across oncology, women’s health, and organ health. The position is eligible for additional compensation and benefits through the company’s Total Rewards program.

Requirements

PhD in Bioinformatics, Computer Science, Machine Learning, Statistics, or a related quantitative field.
4 to 8+ years of post-PhD experience.
Hands-on experience in cancer genomics or epigenomics.
Strong foundation in quantitative reasoning, statistical analysis, and applied machine learning.
Proven track record of developing computational methods for high-throughput sequencing data analysis.
Strong programming skills, including hands-on experience with Python and its scientific library stack, such as pandas, NumPy, and scikit-learn.
Experience with Linux command-line tools, shell scripting, Git, workflow managers such as Nextflow or Snakemake, and cloud or HPC compute environments.
Ability to conduct hypothesis-driven research, visualize findings, and communicate results orally and in writing.
Experience mentoring or technically leading other scientists.

Nice To Haves

Experience with cell-free DNA or methylation sequencing data.
Experience with deep learning frameworks.

Responsibilities

Drive technical workstreams in a collaborative team, taking methods from problem definition through delivery of final classifiers to downstream validation teams.
Design, implement, and validate novel machine learning and statistical methods for cancer diagnostics.
Establish and promote best practices in model interpretability, uncertainty estimation, and reproducibility.
Design robust feature engineering and extraction pipelines tailored to cfDNA methylation and sequencing data.
Collaborate with molecular biologists on experimental design, data integrity, and quality control.
Mentor other scientists and foster a culture of innovation, collaboration, and scientific excellence.
Lead and actively participate in code and design reviews.
Perform hypothesis-driven research, visualize findings, and summarize results orally and in writing.