Raiz Diagnostics is developing an AI-driven molecular diagnostic platform designed to classify lymphoma subtypes directly from transcriptomic data obtained from routine biopsy specimens. The platform combines next-generation sequencing with machine learning to deliver rapid, scalable lymphoma diagnosis and subtype classification.

Our goal is to replace complex multi-test diagnostic workflows with a single sequencing-based assay that produces accurate subtype predictions faster and more consistently than current diagnostic pathways.

We are seeking a Senior Bioinformatics / Machine Learning Scientist to lead development of the computational pipeline powering our diagnostic platform. This individual will architect the full analytical workflow from sequencing data to diagnostic classification and will play a central role in bringing this technology into real clinical use.

This role is a foundational technical position within the company and reports directly to the CEO and scientific founder.

Role Overview

The successful candidate will design and implement the end-to-end computational pipeline that converts sequencing data into clinically interpretable lymphoma subtype predictions.

Working closely with the wet-lab assay development team, this scientist will:

• Build the sequencing analysis pipeline
• Train and validate the machine learning classifier
• Define quality control and diagnostic decision thresholds
• Deliver a reproducible workflow suitable for CLIA laboratory deployment

The role requires strong scientific and technical ownership, close collaboration with laboratory scientists, and the ability to translate research workflows into robust clinical analysis pipelines.

Key Responsibilities

Diagnostic Pipeline Development

• Design and implement the end-to-end sequencing analysis pipeline from FASTQ files to diagnostic classification output
• Build workflows for alignment, expression quantification, quality control, and feature extraction
• Develop reproducible computational workflows suitable for regulated clinical environments

Machine Learning Classifier Development

• Train and optimize machine learning models to classify lymphoma and lymphoma subtypes from transcriptomic data
• Work with a large training cohort of clinically adjudicated cases
• Implement robust validation strategies including cross-validation, calibration, and subtype performance analysis
• Define classification confidence thresholds and indeterminate result rules

Assay and Platform Development

• Evaluate sequencing strategies including Oxford Nanopore long-read transcriptomics and Illumina RNA-seq
• Collaborate closely with the wet-lab scientist to optimize assay design, sequencing parameters, and quality control thresholds
• Ensure computational methods align with assay performance and clinical requirements

Clinical Pipeline Implementation

• Implement version-controlled and reproducible pipelines suitable for CLIA laboratory workflows
• Support development of validation documentation and computational traceability
• Work with regulatory consultants and clinical partners to support diagnostic validation

Technical Leadership

• Serve as the computational lead for the platform
• Help shape future computational infrastructure and team expansion
• Mentor additional bioinformatics or data science hires as the company grows
• Help build and establish effective AI usage across the business, bringing AI-assisted tools into day-to-day workflows beyond the diagnostic pipeline

Required Qualifications

• MS, PhD, or equivalent industry experience in computational biology, bioinformatics, machine learning, computer science, or a related field
• Strong experience developing machine learning models for biological or genomic data
• Experience building bioinformatics pipelines for sequencing data
• Proficiency in Python or R and scientific computing workflows
• Experience working with large biological datasets and implementing robust validation strategies
• Ability to work independently and drive technical development in a startup environment
• Comfort working with AI-assisted coding tools (e.g. coding copilots /agentic developer tools), and interest in helping establish AI usage across the company

Preferred Qualifications

• Experience with RNA-seq or transcriptomic data analysis
• Familiarity with sequencing technologies such as Oxford Nanopore or Illumina
• Experience building reproducible pipelines using workflow systems such as Nextflow, Snakemake, or similar tools
• Experience working with clinical genomics or molecular diagnostics
• Familiarity with software practices supporting regulated environments including version control, reproducibility, and documentation

Clinical Impact

The platform is designed to improve access to expert-level lymphoma diagnosis across diverse healthcare environments. Today, accurate lymphoma classification often requires complex multi-test workflows and subspecialty pathology expertise that may not be available in many community hospitals or regional medical centers.

By combining scalable sequencing workflows with machine learning classification, the technology aims to enable rapid, high-quality molecular diagnosis across academic centers, community hospitals, and health systems that lack specialized diagnostic infrastructure.

Over time, this approach has the potential to expand access to accurate cancer diagnostics both across the United States and globally.

What Makes This Role Unique

• Opportunity to build the core computational engine of a new molecular diagnostic platform
• Direct collaboration with leadership and clinical experts
• Work at the intersection of genomics, machine learning, and clinical oncology
• Significant technical ownership with the ability to shape the company’s future computational team

Location

Los Angeles / UCLA area preferred, with flexibility for exceptional candidates.

Benefits:

• 401(k)
• 401(k) matching
• Health insurance
• On-site gym
• Paid time off
• Vision insurance

Work Location: In person