Staff Machine Learning and Bioinformatics Scientist (Multi-Cancer Early Detection)

Remote; San Francisco (CA); On-site; USD 170,000 - 250,000; Full time

Job summary

Natera’s Research team is developing tests to detect multiple cancers from a single blood draw. We seek a Staff Machine Learning and Bioinformatics Scientist to design models at the heart of this effort, leveraging large-scale genomic data and collaborating with biology and clinical teams.

You will drive novel methods from prototype to scalable implementation and clinical validation, mentoring junior scientists and advancing scientific excellence.

Qualifications

• PhD in Computer Science, Mathematics, Bioinformatics, or related quantitative field.
• Hands-on experience developing novel statistical/ML methods for complex biological data.
• Proven track record of innovation and leadership in method development.
• Expertise in deep learning and multimodal foundation models.
• Proficient in Python and its scientific computing ecosystem.
• Strong scientific rigor and curiosity across R&D processes.
• Excellent communication and collaboration across teams.

Responsibilities

• Lead development of novel statistical and ML methods for cancer signal detection on multi-modal genomic data.
• Build interpretable, well-calibrated models with robust uncertainty estimation.
• Prototype, test and productionize ML models using scalable infrastructure.
• Own key deliverables and shape the team’s research roadmap.
• Collaborate with molecular biologists and clinical experts on experiments and validation.
• Mentor junior scientists and promote curiosity and collaboration.
• Translate results into clear stories for technical and non-technical audiences.

Skills

Python

Deep learning

Multimodal models

Statistical methods

Communication

Education

PhD in CS/Math/Bioinformatics

Tools

Python ecosystem

Job description

Natera’s Research team is building tests that can detect many cancers from a single blood draw. We are looking for a Staff Machine Learning and Bioinformatics Scientist to help design the models at the heart of that effort. You’ll work with large-scale, multi-modal genomic datasets from clinical cohorts and partner closely with molecular biologists and clinical scientists. Your research will advance the state-of-the-art and you will drive new methods from prototype, through scalable implementation, toward clinical validation and, ultimately, to patients.

PRIMARY RESPONSIBILITIES:

• Lead the development of novel statistical and machine learning methods for cancer signal detection on multi-modal genomic data
• Build interpretable, well-calibrated models, setting the standard for uncertainty estimation and reproducibility across the group
• Prototype, test and productionize ML models using scalable infrastructure
• Own key technical deliverables within larger projects and help shape the team’s research roadmap
• Collaborate closely with molecular biologists and clinical experts on design and analysis of experiments and validation studies
• Keep raising the bar through code and design reviews across projects
• Translate complex results into clear stories for technical and non-technical audiences
• Mentor junior scientists and champion a culture of curiosity, collaboration, and scientific excellence

QUALIFICATIONS:

• PhD in Computer Science, Mathematics, Bioinformatics, or a related quantitative field with 6-12 years of experience post-PhD
• Hands-on experience developing novel statistical / ML analysis methods applied to complex biological data
• Proven track record of innovation and technical leadership in complex method development projects
• Expertise in deep learning and multimodal foundation models
• Proficient in Python and its scientific computing ecosystem
• Scientific rigor throughout the R&D process, with eagerness to teach and learn new computational methods and biology
• Excellent communication skills and a collaborative approach across teams

Preferred Experience:

• Familiarity with DNA methylation and other epigenomic data
• Experience with cell-free DNA and liquid biopsy samples
• Background in cancer genomics and diagnostics
• Hands-on work with multimodal foundation models applied to biological data