Zephyr is looking to solve the problem of cancer and other chronic diseases by aggregating massive data sets and harnessing advanced technologies and AI to increase understanding of biology and transform how new therapies are developed and how patients are treated.
Requirements
- Deep expertise in NGS data analysis, including a strong understanding of standard tools (e.g., BWA, STAR, GATK, SAMtools) and algorithms for variant calling, expression quantification, and quality control.
- Proficiency in Python and its scientific computing ecosystem (pandas, NumPy, scikit-learn).
- Experience in precision oncology, immuno-oncology, liquid biopsy analysis (ctDNA, MRD), or AI-driven drug discovery.
- Solid understanding of molecular biology, genetics, and genomics.
- Machine Learning: Experience with or a strong understanding of machine learning concepts and their application to biological data.
- Pipeline & Workflow Orchestration: Proven experience building and managing production-grade bioinformatics pipelines using workflow managers such as Dragster and Nextflow.
- Public Datasets: Hands-on experience with large-scale public cancer genomics datasets (e.g., TCGA, GENIE, DepMap)
Responsibilities
- Design, build, and maintain robust, scalable bioinformatics pipelines for processing and analyzing next-generation sequencing (NGS) data (e.g., WGS, WES, RNA-seq, ctDNA/liquid biopsy).
- Perform rigorous quality control and statistical analysis of high-throughput biological data to ensure data integrity and generate actionable insights.
- Integrating genomics, transcriptomics, and real-world clinical data (EHR, claims) to provide actionable biological insights.
- Write clean, well-documented, and production-ready Python code, leveraging modern workflow orchestration tools like Dagster and/or Nextflow.
- Collaborate closely with computational biologists and machine learning scientists to prepare datasets for model training.
- Clearly communicate complex computational results and biological insights to colleagues with diverse scientific backgrounds.
- Apply rigorous statistical analyses and contribute to machine learning models that integrate genomic, transcriptomic, and clinical data.
Other
- Ph.D. in Bioinformatics, Computational Biology, Genetics, or a related quantitative field. (Exceptional candidates with an M.S. or B.S. and relevant industry experience will also be considered).
- A collaborative, problem-solving mindset and excellent communication skills.
- Strategic & Analytical Mindset: You synthesize complex genomic data to answer key scientific questions, aligning your work with broader organizational goals and understanding its business implications.
- Proactive & Organized Execution: You demonstrate a commitment to quality and accuracy, proactively planning and prioritizing work to efficiently manage projects and deliver results.
- Collaborative Communicator: You clearly articulate complex scientific concepts and listen effectively, fostering collaboration within multidisciplinary teams.
