Principal Scientist Algorithm Lead

NeoGenomics Laboratories

1d•Remote

About The Position

NeoGenomics is looking for a Principal Scientist Algorithm Lead – Clinical NGS Diagnostics who wants to learn to continue to learn in order to allow our company to grow. This is a remote position. As an employer, we promise to provide you with a purpose driven mission in which you have the opportunity to save lives by improving patient care through the exceptional work you perform. Together, we will become the world's leading cancer reference laboratory.

Requirements

PhD in Bioinformatics, Computational Biology, Computer Science, Statistics, or a related quantitative field.
8+ years of experience developing algorithms for clinical NGS diagnostics, ideally in oncology.
Deep expertise in SNV/indel, CNV, SV, fusion, and RNA analysis, NGS QC metrics, statistical modeling, and analytical performance evaluation.
Demonstrated leadership in analytical validation and regulatory submissions (CLIA, CAP, FDA, NYDoH, MolDx).
Hands‑on experience applying AI/ML methods to NGS data or biomarker development.
Expert programming skills in Python and R; strong understanding of workflow orchestration and validation automation.
Strong publication or presentation record in computational genomics or NGS diagnostics.
Experience building QC‑driven, highly automated validation pipelines with rigorous statistical controls.
Familiarity with payer evidence and reimbursement considerations for molecular diagnostics.

Responsibilities

Own the full lifecycle of clinical NGS algorithms under design control, including requirements definition, risk analysis, traceability to analytical claims, and design change impact assessment.
Architect and lead automated analytical validation frameworks spanning accuracy, precision, sensitivity/LOD, specificity, linearity, and robustness for SNVs, indels, CNVs, structural variants, gene fusions, and RNA‑based assays.
Define algorithm‑level error models, performance budgets, and acceptance criteria, driving systematic improvements in low‑VAF detection, background suppression, and assay‑specific artifact mitigation.
Establish statistically rigorous approaches for truth set construction, reference materials, in silico mixing, and synthetic data generation to support scalable and reproducible validation.
Serve as final technical authority on algorithm changes, including re‑validation scope, documentation strategy, and regulatory impact.
Lead development and optimization of variant calling and signal extraction algorithms for DNA‑ and RNA‑based assays, including ultra‑deep sequencing and challenging genomic regions.
Develop and track NGS‑based quality control metrics at the read, molecule, sample, and assay levels (e.g., coverage, uniformity, duplication/UMI yield, error rates, contamination, noise profiles) to monitor analytical performance and stability.
Apply probabilistic modeling, Bayesian inference, and machine learning to improve sensitivity and specificity while maintaining interpretability and regulatory defensibility.
Lead algorithm development for solid tumor and hematologic malignancy profiling, including tissue and liquid biopsy use cases.
Address challenges specific to low‑input DNA/RNA, fragmented cfDNA, and ultra‑low‑allele‑frequency variants.
Translate algorithm behavior and QC performance into clear, testable analytical claims aligned with CLIA, CAP, FDA, NYDoH, CLSI, and MolDx expectations.
Author and review algorithm components of validation reports, design history documentation, and regulatory submissions.