Staff Deep Learning/AI Engineer

What if the work you did every day could impact the lives of people you know? Or all of humanity?

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 that are transforming human health through the early detection and diagnosis of diseases and new treatment options for patients.

Working at Illumina means being part of something bigger than yourself. Every person, in every role, has the opportunity to make a difference. Surrounded by extraordinary people, inspiring leaders, and world changing projects, you will do more and become more than you ever thought possible.

The Role:  Staff Deep Learning Engineer

Our team develops Next Generation Sequencing (NGS) solutions used by researchers and clinicians worldwide, providing sample-to-answer pipelines with high reliability, speed, and accuracy of results.  We develop machine learning solutions across Illumina’s portfolio, from sequencing functions to analysis and interpretation algorithms. DRAGEN, our secondary analysis platform, has industry leading performance and is used for clinical and research work. We also develop algorithms for on-sequencer pipelines including super-resolution, basecalling, denoising. Advanced AI applications drive transformational genetic insights that improve understanding of human biology, cancer and rare disease.

We are seeking a Staff ML Algorithms engineer to join our team. This role will develop and implement ML systems across Illumina’s products, including DRAGEN and high-throughput sequencing systems like NovaseqX, the industry-leading platform. You will collaborate with cross-functional teams (algorithms, implementation, bioinformatics, optics and imaging, test) to implement machine learning algorithms operating on a variety of data types (images, sequencing output, population data, DNA, RNA, multi-omics, etc.) 

If you have product development experience and a passion for machine learning, this is a great opportunity to join a team developing complex ML algorithms at a leading biotech company.

Responsibilities:

• You will develop machine learning algorithms in Python and deliver products that are deployed on the cloud, on sequencers and on local compute servers (using Python, C++, also FPGA, GPU/CUDA)
• Research complex algorithms for primary and secondary analysis, deliver best-in-class products
• Create and maintain Python models and pipelines, documentation, unit tests 
• Working closely with other software engineers, researchers and domain experts on AI/ML models and architectures
• Work with experts across software engineering, hardware engineering, ML and data science, optics and imaging, embedded systems, test 
• Help advanced code quality and efficiency throughout ML development; deliver efficient solutions to optimize pipeline speed (DRAGEN is FAST!)
• Design, develop, test, deploy, maintain software solutions (on sequencer, on DRAGEN servers, in the cloud)
• Deliver high quality documentation and test cases
• Debug and troubleshoot ML models

Qualifications:

• Bachelors or Masters in Computer Science, Engineering or a related technical field, or equivalent experience 
• 7+ years of relevant experience in algorithm development, ideally Python and C++, especially high-performance computing 
• Experience with large and complex pipelines, using machine learning models, signal processing (or similar) to analyze large volumes of data efficiently, from algorithm research and evaluation through detailed implementation; ideally experience in shipping products
• Experience in image processing, algorithms and data structures, numerical optimization, parallel and distributed computing, high-performance computing, embedded systems, machine learning
• Ideally experience with ML frameworks (Tensorflow, keras, Pytorch, xgboost, sklearn or similar)
• Solid Python coding skills – experience with unit testing, code reviews, version control
• Statistical skills to identify modeling issues and drive accuracy improvements 
• Self-starter, good problem-solving skills, ability to push forward project objectives both through individual effort and team collaboration.

Additional Nice-to-Haves:

• Bioinformatics, ML, software engineering principles, software test, applied math background and/or experience
• Deep learning, structured data machine learning, gradient boosting, linear algebra and statistics applied to images, tabular data, unstructured multimodal data, computer vision
• Hardware skills e.g. optical sys