Responsibilities
- Serve as a key thought-leader on the Computational Science team, leading the analysis and interpretation of cancer's molecular signatures and staying current with the field.
- Guide and contribute to the development of models that characterize biological changes associated with cancer.
- Execute rigorous computational analyses on data from best-in-class molecular assays, including whole genome sequencing, whole genome bisulfite sequencing, targeted sequencing, RNA sequencing, and protein quantitation.
- Design novel statistical models for the evaluation, characterization, and modeling of these data types within the context of cancer biology and progression.
- Identify research hypotheses and potential areas for model improvement; plan, scope, and execute associated research projects with a skilled team of computational biologists.
- Solve complex analytical challenges inherent to the study of cell-free circulating nucleic acids and proteins.
- Partner closely with molecular biologists to collaboratively refine wet lab experiments, and with development scientists to turn research models into products.
- Support the professional development and career growth of talented, cross-functional computational biologists within your team.
Requirements
- PhD or equivalent experience in a relevant quantitative field (e.g., computational biology, cancer biology, statistics, bioinformatics).
- At least 8 years of post-PhD experience applying computational techniques for biological discovery and product development, preferably in cancer or diagnostics within an industry setting.
- Deep expertise in cancer and molecular biology, with a proven ability to leverage this knowledge for computational biology and diagnostics problems in cancer.
- Extensive experience analyzing data and developing models for high-throughput, quantitative technologies in genomics, epigenomics, transcriptomics, proteomics, (e.g., Methyl-seq, ATAC-seq, RNA-seq, Hi-C, immunodetection assays).
- Proficiency in computational and programming skills, including extensive experience with Python statistical packages (Numpy, Matplotlib, Pandas) and modeling packages (Scikit-learn, TensorFlow, PyTorch) or equivalents in languages like R or C/C++.
Nice to Have
- Experience training, evaluating, or applying biological sequence models—specifically sequence-to-function models that learn and predict functional biology directly from raw DNA, RNA, or protein sequences.
- Experience developing or applying single-cell genomic or transcriptomic models to translate biological heterogeneity into generalizable regulatory or epigenomic signatures.
- Experience modeling cell-free DNA (cfDNA) signals specifically for early disease detection and diagnostic applications.
Benefits
- Equity
- Cash bonuses
- Full range of medical, financial, and other benefits depending on the position offered.
Work Arrangement
Hybrid — Brisbane, California
