Principal Bioinformatics Scientist

As a Principal Bioinformatics Scientist at AccuScan Sciences, you will lead the development and improvement of statistical and algorithmic methods for NGS-based variant detection and minimal residual disease (MRD) calling. This role focuses on tumor/normal variant calling in tissue samples as well as ultra-low-frequency mutation detection in cfDNA.

You will work closely with assay development, bioinformatics engineering, and R\&D teams to translate new technologies into robust, production-ready analytical pipelines. The ideal candidate brings deep statistical modeling expertise, strong hands-on implementation skills, and experience working with WGS or large-scale sequencing data. Prior exposure to regulated (FDA/IVD) environments and machine learning is a strong plus.

Key Responsibilities

• Provide scientific and technical leadership for the design, evolution, and long‑term roadmap of somatic variant‑calling methods for tumor tissue and cfDNA applications
• Lead the development, validation, and optimization of MRD‑calling algorithms, setting standards for sensitivity, specificity, robustness, and clinical relevance
• Define and own benchmarking frameworks, performance metrics, and QC strategies used to evaluate analytical methods across platforms, assays, and data types
• Serve as a senior technical authority for troubleshooting complex analytical and pipeline issues, performing root‑cause analysis, and driving durable, system‑level solutions
• Architect and implement production‑grade algorithms, partnering with bioinformatics engineering to ensure scalability, reliability, and maintainability of analytical pipelines
• Act as a key scientific partner to assay development teams, shaping experimental design, data analysis strategies, and algorithmic adaptations for new and evolving technologies
• Establish best practices for analytical documentation, validation reporting, and design controls; communicate technical trade‑offs, limitations, and recommendations to senior technical, clinical, and cross‑functional stakeholders

Requirements

• Ph.D. in Statistics, Biostatistics, Computer Science, Bioinformatics, Computational Biology, Applied Mathematics, or a related field, with 8\+ years of domain experience
• Strong foundation in statistical inference and modeling, including uncertainty quantification and decision thresholding
• Prior experience working with genomics data, including WGS or large-scale NGS datasets, and a solid understanding of technical and biological noise sources
• Familiarity with standard genomics data formats and tooling (e.g., FASTQ, BAM/CRAM, VCF) and common processing workflows
• Demonstrated software implementation skills in Python and/or a performance-oriented language (e.g., C\+\+, Rust, Java), with experience writing maintainable, testable, production-quality code
• Excellent communication and collaboration skills, with the ability to work effectively across research, engineering, and assay development teams
• Hands-on experience with cfDNA analysis and/or MRD detection, including ultra-low-frequency variant calling and/or epigenetics-based analyses
• Machine learning experience, particularly in settings involving class imbalance, model evaluation, calibration, and decision optimization
• Experience collaborating closely with assay development teams on experimental design, data analysis planning, and iterative assay optimization
• Experience working in regulated product development environments (e.g., FDA, IVD), including documentation practices, analytical validation, and design controls

Benefits

• Health Care Plan (Medical, Dental \& Vision)
• Retirement Plan (401k, IRA)
• Paid Time Off (Vacation, Sick \& Public Holidays)