Staff Machine Learning Scientist - Translational AI

Serve as a scientific and technical authority on the application of molecular, genomic and pathology foundation models to translational and clinical questions.

Define modeling strategies that bridge pretrained foundation models and downstream translational use cases.

Review and elevate modeling approaches used by other scientists through technical feedback and mentorship.

Lead the application and post-training of foundation models (deep sequence, multimodal, representation learning) for biomarker discovery, outcome prediction, molecular recurrence modeling, and therapy response assessment.

Design fine-tuning, probing, and representation analysis workflows that extract biologically interpretable signals from large models.

Ensure modeling outputs are aligned with biological plausibility, clinical relevance, and downstream decision-making needs.

Build and evaluate advanced ML models across genomics, transcriptomics, ctDNA, imaging, and clinical metadata.

Design clinical investigation and evaluation frameworks that connect model performance to translational utility, robustness, and real-world constraints.

Identify failure modes, sources of bias, and uncertainty, and propose mitigation strategies appropriate for clinical-facing applications.

Partner deeply with translational science, bioinformatics, medical, and clinical teams to frame high-value AI questions.

Act as a technical bridge between research, platform, and engineering teams to ensure scalable and reproducible workflows.

Contribute to external collaborations and strategic partnerships related to foundation models and translational AI.

Drive scientific storytelling around translational AI efforts through internal reviews, leadership updates, and external-facing materials.

Contribute to peer-reviewed publications, conference submissions, and invited talks.

Help establish Natera’s external reputation in foundation models for translational medicine.

PhD in Computational Biology, Bioinformatics, Computer Science, or a related quantitative field.

5+ years of experience applying ML to biological, genomic, or clinical data, in the field of oncology, immunology, or translational medicine..

Deep experience with foundation models, representation learning, self-supervised learning, or deep sequence models.

Demonstrated ability to translate ML outputs into biological insight or clinical value, not just metrics.

Strong proficiency in PyTorch and modern ML tooling (e.g., HuggingFace transformers, PEFT, Captum, MLFow).

Track record of scientific and technical leadership through project ownership, mentorship, or cross-team influence.

Experience integrating genomics with imaging or clinical data in multimodal foundation models.

Experience with drug discovery, clinical trial data, real-world evidence, or regulatory-facing analyses.

Strong publication record in ML, computational biology, or translational research venues.

Serve as a scientific and technical authority on the application of molecular, genomic and pathology foundation models to translational and clinical questions.

Define modeling strategies that bridge pretrained foundation models and downstream translational use cases.

Review and elevate modeling approaches used by other scientists through technical feedback and mentorship.

Lead the application and post-training of foundation models (deep sequence, multimodal, representation learning) for biomarker discovery, outcome prediction, molecular recurrence modeling, and therapy response assessment.

Design fine-tuning, probing, and representation analysis workflows that extract biologically interpretable signals from large models.

Ensure modeling outputs are aligned with biological plausibility, clinical relevance, and downstream decision-making needs.

Build and evaluate advanced ML models across genomics, transcriptomics, ctDNA, imaging, and clinical metadata.

Design clinical investigation and evaluation frameworks that connect model performance to translational utility, robustness, and real-world constraints.

Identify failure modes, sources of bias, and uncertainty, and propose mitigation strategies appropriate for clinical-facing applications.

Partner deeply with translational science, bioinformatics, medical, and clinical teams to frame high-value AI questions.

Act as a technical bridge between research, platform, and engineering teams to ensure scalable and reproducible workflows.

Contribute to external collaborations and strategic partnerships related to foundation models and translational AI.

Drive scientific storytelling around translational AI efforts through internal reviews, leadership updates, and external-facing materials.

Contribute to peer-reviewed publications, conference submissions, and invited talks.

Help establish Natera’s external reputation in foundation models for translational medicine.

PhD in Computational Biology, Bioinformatics, Computer Science, or a related quantitative field.

5+ years of experience applying ML to biological, genomic, or clinical data, in the field of oncology, immunology, or translational medicine..

Deep experience with foundation models, representation learning, self-supervised learning, or deep sequence models.

Demonstrated ability to translate ML outputs into biological insight or clinical value, not just metrics.

Strong proficiency in PyTorch and modern ML tooling (e.g., HuggingFace transformers, PEFT, Captum, MLFow).

Track record of scientific and technical leadership through project ownership, mentorship, or cross-team influence.

Experience integrating genomics with imaging or clinical data in multimodal foundation models.

Experience with drug discovery, clinical trial data, real-world evidence, or regulatory-facing analyses.

Strong publication record in ML, computational biology, or translational research venues.