Principal Deep Learning/AI Engineer - Bioinformatics

1w1 week ago

Illumina

San Diego, US · Full-time · $205,100 – $307,700

About this role

At Illumina, we are expanding access to genomic technology to realize health equity for billions of people around the world. Our efforts enable life-changing discoveries transforming human health through early detection, diagnosis, and new treatments. The Principal Deep Learning/AI Engineer in Bioinformatics is a senior hands-on technical expert powering sequencing and analysis products.

This role involves inventing, implementing, and validating AI- and ML-driven bioinformatics methods with deep personal ownership of algorithm design, model development, benchmarking, and production readiness. You will design, prototype, and implement AI/ML for genomics and multiomics like basecalling, variant calling, error modeling, and single-cell analysis. Partners with product and engineering ensure methods are scientifically sound and performant at scale.

Lead a focused team to create, enhance, and sustain ML and AI products while providing technical direction and mentorship. Serve as technical authority for AI features from concept through production. Surround yourself with extraordinary people, inspiring leaders, and world-changing projects.

Drive data-centric AI leadership including curation, labeling, and bias analysis across instruments and populations. Enable adoption through models improving accuracy, speed, cost, and usability. Every role at Illumina offers opportunity to make a difference and become more than you thought possible.

Requirements

PhD (strongly preferred) or MS with equivalent depth in Bioinformatics, Computational Biology, Computer Science, Statistics, or a related field
10+ years of hands-on experience developing algorithms and ML models for biological data, with sustained personal technical contributions
Typically requires minimum of 15 years related experience with Bachelor’s degree; or 12 years with Master’s; or PhD with 8 years
Deep expertise in AI/ML for genomics applications like basecalling and variant calling
Experience with production ML pipelines, inference efficiency, and regression detection
Proficiency in data curation, labeling, augmentation for biological datasets
Strong skills in benchmarking, validation metrics, and statistical approaches for bioinformatics models

Responsibilities

Design, prototype, and implement AI/ML methods for genomics and multiomics (e.g., basecalling, variant calling, error modeling, QC, anomaly detection, methylation, single-cell, metagenomics, assembly, interpretation)
Serve as technical authority for AI features embedded in Illumina software and pipelines, from concept through production release
Lead a focused team to create, enhance, and sustain ML and AI products and tools
Define gold-standard datasets, evaluation metrics, and statistical validation approaches; review and approve model performance and scientific claims
Work with engineers to ensure models are reproducible, versioned, monitored, and robust in production
Drive data strategy for model performance, including curation, labeling, augmentation, and bias/edge-case analysis
Lead architecture and design reviews for AI and bioinformatics components; set coding, testing, and documentation standards
Provide technical input for regulated and clinical readiness including design controls and validation