Bioscope AI is an innovative company focused on transforming precision medicine through advanced AI technologies. They are seeking a Senior Bioinformatics Scientist/Engineer to design and validate clinical-grade genomic pipelines, collaborating with various experts to enhance clinical interpretations for physicians.
Responsibilities:
- Architect and optimize clinical genomics pipelines in your area of expertise: PGx track: Star-allele calling pipelines (e.g., CYP2D6, CYP2C19, DPYD, TPMT) handling complex structural variation, gene duplications, and hybrid alleles
- PRS track: Polygenic risk scoring pipelines with integrated multi-ancestry PRS models and clinical calibration utilizing traditional WGS SNV/INDEL variant calling plus phenotypic data
- Extend existing 30X WGS infrastructure to support robust feature extraction and clinical annotation
- Curate and maintain annotation stacks integrating domain-specific databases (PharmGKB, CPIC, PharmVar, PGS Catalog) and proprietary AI-derived knowledge graphs
- Build automated cadenced updates of clinical-grade knowledge sources to feed the AI engine
- Implement validation, reproducibility, and audit trails; pipeline change-control logs; briefing decks
- Partner with software and AI engineers to integrate genomic features into AI models
- Participate in cross-team design reviews and internal workshops on clinical curation and validation
Requirements:
- PhD (or MS with 5+ yrs experience) in Genetics, Genomics, Bioinformatics, Computational Biology, or related field
- 4+ yrs deep expertise in one of the following: Pharmacogenomics: star-allele calling, diplotype assignment, phenotype prediction, complex locus resolution
- 4+ yrs deep expertise in one of the following: Polygenic risk scoring: PRS development (PRS-CS, LDpred, etc.), multi-ancestry methods, clinical calibration, integrated scoring with phenotypic+monogenic data
- Solid grasp of variant calling (DRAGEN, GATK), structural variant/copy number variant detection, and functional annotation methods
- Proficiency in Python for production-grade code, full unit-test coverage, REST API usage, reproducible statistical analysis, and visualizations; AWS database resource familiarity
- Experience working in an agile based software organization, clearly documenting ticketed work, and modifying code in git-tracked production code bases
- Comfort with AWS services (Lambda, Fargate, Step Functions, Glue, Athena)
- Highly comfortable with AI-based development tools (Claude Code, Cursor, OpenAI Agents)
- Exposure and familiary with other 'omics' (proteomics, epigenomics, transcriptomics)
- Strong communication skills—able to translate genomic insights into plain language for physicians, regulators, and engineers
- Experience contributing to or curating clinical-grade databases in your domain
- Prior authorship of clinical validation studies published in peer-reviewed journals
- Experience integrating multi-omics datasets or developing multi-modal AI features