Natera is seeking a Lead/Staff Machine Learning and Bioinformatics Scientist to implement and expand state-of-the-art machine learning methods to enhance their product portfolio in oncology, specifically focusing on Epigenomics.
Requirements
- Demonstrated experience in developing core ML models, including generalized linear models, kernel methods, tree-based algorithms, and neural networks, with a focus on biological data (e.g., DNA sequencing data)
- Profound understanding of deep learning models, large language models (LLMs), and multimodal foundation models
- Proficient in Python and its scientific computing ecosystem (e.g., NumPy, Pandas, Scikit-learn)
- Experience with ML frameworks such as PyTorch, TensorFlow, or JAX; familiarity with LLM-specific tools like LangChain; and model deployment via platforms like HuggingFace
Responsibilities
- Develop and validate cutting-edge machine learning methods to solve problems in diagnostics
- Contribute to model interpretability, uncertainty estimation, and reproducibility best practices
- Design robust feature engineering and extraction pipelines tailored to biological data
- Prototype and productionize models using scalable ML infrastructure tools such as MLflow, Airflow, and Docker
- Collaborate closely with molecular biologists on experimental design and quality control
- Actively participate in code and design reviews
Other
- PhD in Computer Science, Statistics, Bioinformatics, or a related quantitative field with 6-12 years of experience post-PhD.
- Excellent cross-functional communication skills
- A strong eagerness to both teach and learn about new machine learning methods and biology concepts
- Position is available as a hybrid position in San Carlos, Bay Area, California as well as a remote position (within US).
