Job Description

Sema4 is a patient-centered health intelligence company founded on the idea that more information, deeper analysis, and increased engagement will improve the diagnosis, treatment, and prevention of disease. Sema4 is dedicated to transforming healthcare by building dynamic models of human health and defining optimal, individualized health trajectories, starting in the areas of reproductive health and oncology. Centrellis™, our innovative health intelligence platform, is enabling us to generate a more complete understanding of disease and wellness and to provide science-driven solutions to the most pressing medical needs. Sema4 believes that patients should be treated as partners, and that data should be shared for the benefit of all.

The BIOINFORMATICS PRODUCT ENGINEER/PRODUCT MANAGER supports computational pipeline products that convert next-generation sequencing (NGS) data to insights about the molecular makeup of patient cells. These products are the core of sophisticated clinical diagnostics serving thousands of patients per week and also enable high-volume research projects in human disease. As part of the Somatic Genomics R&D group in the Bioinformatics R&D department, the Product Manager will work closely with the scientific director and the lead engineer of each pipeline product to define and execute the translation of scientific and engineering innovation into high-throughput analysis methods for a data sciences company. The product manager is responsible for clear definition and timely delivery of the pipeline products and their successful integration and deployment as part of Sema4’s data sciences platform built by collaborative inter-disciplinary teams (science, engineering, clinical, and business/product).

RESPONSIBILITIES

• Own and manage the roadmap, feature backlog, work plan, and release schedule for a portfolio of NGS data pipeline products by closely working with scientific, clinical, business, product, scientific compute/IT, and project management teams to translate innovative bioinformatics R&D to high-performance production methods that serve business needs.
• Translate business requirements for these pipelines to detailed technical requirements, designs, specifications, and work definitions for scientific and engineering teams.
• Carry out detailed design and write technical specifications for features, workflows, data flows, application programming interfaces (APIs), file formats, data schemas, and data payloads used within these data pipelines as well as for communication with other products in the Sema4 analytics ecosystem.
• Estimate product delivery time, effort, risks, and dependencies in collaboration with project management on other teams, as well as communicate status updates between all levels.
• Communicate about complex technical/scientific problems between teams and stakeholders at all levels and work with them to solve, as well as generally facilitate inter-team communication by mocking up illustrative examples that help people from diverse backgrounds find a common understanding.
• Support the data pipeline products for a multitude of users and data consumers at Sema4 by becoming a subject matter expert and serving as the products’ primary representative and contact person, including providing training.
• Co-lead the execution and continuous improvement of the software development life cycle (SDLC) of the data pipeline product portfolio.
• Write and maintain clear business and technical documentation for target audiences from various backgrounds (scientific, software/IT, clinical, business, project management).

QUALIFICATIONS

• Master’s or PhD degree in a relevant computational or biomedical field.
• Minimum 3 years of relevant post-graduate experience, e.g. software product development, software engineering or programming, data science or analysis, bioinformatics/genomics research, systems engineering.
• Excellent written and verbal communication, including via visualizations, on inter-disciplinary teams about complex technical topics.
• Experience with data and process standardization in bioinformatics (specifically, genomics and transcriptomics of humans), e.g. common variation databases (dbSNP, gnomAD, COSMIC), HGVS, ClinGen, common file formats (BAM, VCF, GFF, etc.) for NGS data and genomic and transcriptomic variation.
• Experience with bioinformatics pipelines for data analysis, especially for variant calling (SNV/indel, fusion, structural variant, CNV, etc.) or genomic biomarker characterization (MSI, TMB, mutational signatures, etc.).
• Some programming experience, especially in Python, R, and SQL.
• Familiarity with cloud engineering of high-throughput, computationally intensive data processing pipelines and methods.
• Experience with WDL, CWL, or any domain-specific language for workflow modeling.