Staff Scientist, Machine Learning (Genomics)

Natera is seeking a highly motivated Staff Machine Learning Scientist to join our rapidly growing company. As a member of the Data Science research team you will participate in the design and prototyping of cutting edge algorithms for analysis of genetic and clinical data. You will perform data analysis, algorithm design, contribute to our intellectual property portfolio, and interact closely with R&D and product teams to define the requirements and improve the products and processes.

PRIMARY RESPONSIBILITIES:

• ML/DL Research Leadership: Lead research on machine learning and deep learning models using NGS data. Frame the problem, choose the approach, and decide when a model has earned the next round of investment. This is an individual contributor role with Staff-level scope. You will set the technical direction of the work, not just carry out a plan someone else wrote.
• Algorithm and Model Development: Design, build, and benchmark the models and features behind the next generation of Women Health and Organ Health products. Apply statistical learning and deep learning to high-dimensional, noisy, often small-sample sequencing data. Know when a simpler method is the right answer.
• Working with Bioinformatics Pipelines: Work directly with the existing sequencing pipelines and their outputs without needing a bioinformatician to run, change, or interpret them for you. When results look wrong, trace the problem back through each processing step and work out whether it comes from the pipeline, the data, or the biology. Build or extend pipeline components when a project needs it. 
• Study Design and Experimental Partnership: Work with molecular biology and assay development scientists to design experiments. Help decide what data to generate, how much of it, and with what controls so the analysis can answer the question. Troubleshoot experiments alongside the lab, and tell a biology problem from a data or analysis problem.
• Rigor and Documentation: Set the standard for careful analysis on the team: sound validation design, honest performance estimates, no leakage between training and evaluation data, and documentation. Support the group in producing high-quality technical and design documentation.
• Intellectual Property and Scientific Contribution: Contribute to Natera's IP portfolio through invention disclosures and patent work, and to its scientific reputation through publications and presentations where appropriate.
• Technical Leadership and Mentorship: Mentor data scientists and bioinformaticians, review their work, and be the person others bring hard modeling questions to. Make decisions about your own methods with minimal direction, including when the problem is ambiguous, and know when to escalate.
• Ways of Working: AI is a routine part of the work here, including coding agents for implementation, analysis, and review. You own what you ship, whatever produced it. We do not screen for prior experience with these tools, and we provide the tooling and the ramp time.

QUALIFICATIONS:

• M.S. or Ph.D. in a quantitative field such as Computer Science, Applied Mathematics, Statistics, Bioinformatics, Computational Biology, Engineering, or similar. Equivalent depth built through work counts fully.
• 6+ years of hands-on experience in machine learning and data analysis on biological or genomic data after your degree. We count relevant experience from the point your work became substantially independent, however you got there.
• A demonstrated track record of models or algorithms you led that reached real use (a product, a production pipeline, or a decision someone relied on), not only a result.
• We are hiring for depth in NGS, bioinformatics, and machine learning, and we will provide the domain ramp.

KNOWLEDGE, SKILLS, AND ABILITIES:

• Depth in next-generation sequencing data analysis: sequencing QC, alignment and quantification, normalization, and the artifacts that come with them. You should have the judgment to spot a wrong result before someone else does.
• Working fluency with NGS bioinformatics pipelines. You can run them on your own, read their code and logs, follow a result back through each processing step, and diagnose failures or unexpected outputs. You can also build or modify pipeline 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, including open-source ML libraries (e.g., scikit-learn, PyTorch, TensorFlow, XGBoost) in a cloud environment.
• Experience processing large datasets and working with a query language such as SQL.
• A proven ability to apply mathematical and statistical principles to real estimation problems and turn them into practical solutions.
• Familiarity with assay development and analysis pipelines for molecular or clinical biomarkers.
• Clear communication of technical results to people who do not share your background, and a record of delivering complex projects with cross-functional teams.

PREFFERED SKILLS: 

• Experience with RNA-seq, 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 (Nextflow, WDL, Snakemake) and containerization (Docker), enough to read, debug, and extend existing workflows.
• AWS or GCP for large-scale ML training and inference.
• Patents, peer-reviewed publications, or conference presentations.
• A desire to work in a fast-paced environment where a small team has high impact.