Biostatistician – Machine Learning & Bioinformatics

PreludeDx; Laguna Hills (CA); On-site; USD 110,000 - 160,000; Full time

Job summary

PreludeDx is seeking a highly skilled Biostatistician to support development and validation of molecular diagnostics by integrating genomic and proteomic data. You will apply advanced statistics and ML to high-dimensional data, ensure QA of NGS pipelines, and collaborate across assay development, bioinformatics, and clinical research.

The role includes designing statistical models, performing variant analysis, and ensuring reproducible analyses with R and SAS support for regulatory submissions.

Qualifications

• Experience in CLIA/CAP accredited clinical labs.
• Expertise analyzing NGS data (WES, RNA-Seq, panels).
• Proficient in R; SAS for regulatory data is a plus.
• ML techniques applied to biomedical data.
• Familiar with FASTQ, VCF, BAM, GTF formats.

Responsibilities

• Release bioinformatic analyses to support clinical operations.
• Build statistical models and ML algorithms for diagnostics.
• Analyze NGS datasets including variant calling and annotation.
• Develop QA protocols for NGS data pipelines.
• Integrate multi-omic data with cross-functional teams.
• Support study design and regulatory submissions.
• Document analyses, validation, and pipeline specs.
• Write reproducible R code; SAS preferred for regulated data.
• Contribute to publications and scientific communications.

Skills

NGS data analysis

R programming

Machine learning

Bioinformatics pipelines

Cloud computing

Data integration

Git

Regulatory submissions

Communication skills

Education

Biostatistics/Bioinformatics degree

Tools

R

SAS

Bioconductor

AWS

GCP

Job description

Description

We are seeking a highly skilled and motivated Biostatistician to support the development and validation of novel molecular diagnostic tests by integrating genomic and proteomic data. The role will be responsible for working in operations and for the timely release of bioinformatic analyses. The successful candidate will apply advanced statistical and machine learning techniques to analyze high-dimensional data, ensure quality assurance of next-generation sequencing (NGS) pipelines, and collaborate closely with cross-functional teams in assay development, bioinformatics, and clinical research.

Essential Responsibilities

• Release bioinformatics analyses in a timely manner to support clinical operations.
• Design and implement statistical models and machine learning algorithms to support discovery, validation, and performance evaluation of proteomic/genomic based diagnostics.
• Perform bioinformatic analysis of NGS datasets, including variant calling, annotation, and filtering.
• Develop and execute quality assurance protocols for NGS data pipelines and result reproducibility.
• Collaborate with bioinformatics, lab scientists, and software engineers to integrate multi-omic datasets and refine analytical workflows.
• Support study design, statistical analysis plans, and interpretation of findings for both internal R&D and regulatory submissions.
• Write comprehensive documentation, including analysis reports, methods validation, and pipeline specifications.
• Develop reproducible and well-documented code in R, with SAS proficiency preferred for regulatory or clinical data support.
• Contribute to publications and presentations of research findings in scientific and clinical settings.

The above list represents the general duties considered essential functions of the job and is not to be considered an exhaustive description of all the work requirements that may be inherent in the position.

Requirements

EXPERIENCE & QUALIFICATIONS:

• Experience in working within a CLIA and CAP accredited clinical laboratory to support laboratory developed testing (LDTs).
• Strong experience analyzing NGS data, including pipeline QC, normalization, and interpretation (e.g., WES, RNA-Seq, targeted panels).
• Proficiency in R for statistical computing, data visualization, and reproducible research.
• Experience with machine learning techniques (e.g., random forests, support vector machines, regularization, cross-validation) applied to biomedical data.
• Working knowledge of bioinformatics tools and formats (e.g., FASTQ, VCF, BAM, GTF, Bioconductor).
• Experience in data integration from proteomic and genomic platforms is highly desirable.
• Familiarity with SAS for clinical or regulatory submissions is preferred.
• Excellent problem-solving skills, strong attention to detail, and ability to work independently or in teams.
• Experience in regulated FDA environments a plus.
• Familiarity with cloud-based computing (e.g., AWS, GCP) and version control (e.g., Git).
• Background in molecular diagnostics or translational research projects.
• Strong written and verbal communication skills for both technical and nontechnical audiences.

Education

PhD or Master’s degree in Biostatistics, Bioinformatics, Computational Biology, or related discipline.