Sr Research and Development Scientist, Algorithm Developer
Baylor Genetics · United States · 3 wk ago
RemoteRemoteScienceFull-time
Key Responsibilities
- Lead the design, optimization, and implementation of scalable NGS algorithms and pipelines for detection and interpretation of complex genomic features, including SNVs/Indels, CNVs, STRs, methylation, trisomy, PGx variants, and variants in homologous and homopolymer regions
- Lead the design and optimization of targeted NGS panels for existing and new products
- Drive end-to-end development, validation, benchmarking, and integration of NGS algorithms and analysis pipelines using internal and public truth sets
- Collaborate closely with assay scientists, bioinformatics teams, software engineers, and other partners to translate biological and product requirements into computational solutions
- Provide technical and project leadership to ensure analytical accuracy, robustness, scalability, and continuous improvement across products
- Support technology transfer, pipeline updates, and production deployment, and contribute to scientific publications, conference presentations, and intellectual property development
Required Qualifications
- Ph.D. in Bioinformatics, Computational Biology, Genomics, or a related discipline
- Minimum 5 years of experience in NGS algorithm development
- Proficiency in Python, R, C++, and workflow orchestration tools
- Deep understanding of: Read alignment and variant calling (e.g., BWA-MEM, minimap2, GATK, DeepVariant) for germline or/and somatic variants, CNV modeling, STR detection tools and methylation callers, Homologous region analysis and control gene normalization, PGx variant interpretation and allele resolution
- Strong analytical, problem-solving, and communication skills
Preferred Qualifications
- Experience with somatic variant calling by short-reads or/and long-reads sequencing
- Knowledge of machine learning models for variant classification
- Experience with clinical genomics and regulatory standards
- Familiarity with pharmacogenomic databases (e.g., PharmGKB, CPIC)