Bioinformatics Software Engineer (GPU Accelerated)

Prima Mente is a frontier biology AI lab. We generate our own data in our own lab, build general-purpose biological foundation models, and translate discoveries into research and clinical outcomes, in clinical studies we run. Our first goal is to tackle the brain: to deeply understand it, protect it from neurological disease, and enhance it in health. Our team of AI researchers, experimentalists, clinicians, and operators is based in London, San Francisco, and UAE.

Architect, build, and own scalable production pipelines that process multi-omics data for AI model development, moving from hypothesis to patent-ready results in months, not years.

• Design and implement GPU/CPU-native bioinformatics pipelines using Flyte and/or Nextflow for multi-omics data processing at scale (1000+ samples)

• Optimising cost and performance, leveraging GPU/CPU acceleration where it matters

• Work with experimental and machine learning teams to confirm and refine computational findings, and to ensure processing aligns with model needs

• Develop and manage specific external research collaborations with academic and industrial partners

In 1 month you are deploying workflows on GPU/CPU-accelerated cloud infrastructure to process your own multi-omic experiments, while establishing relationships with AI/ML and wet lab teams to understand their requirements.

In 3 months the multiple optimised GPU/CPU-native pipelines you built are processing in the order of 1,000s of samples with high speed improvements and significantly reduced costs, generating publication and patent-ready results.

In 6 months your pipelines run in automatised production feeding daily AI model training You’re co-designing experiments with AI/ML engineers and you’re leading technical execution on external collaborations with industrial and/or academic partners.

You want to redefine what’s possible at the frontier of AI and biology. You’re an engineer, not an analyst. You thrive pushing the boundaries of performance and efficiency and enjoy architecting the systems and making multiple fast technical decisions. You iterate and move fast.

We don’t expect you to check every box. Strong applicants often have depth in some of these and interest in growing into others.

• First-hand deep experience with at least 2-3 large omics types (genomics, transcriptomics, chromatin accessibility, DNA methylation, histone modifications profiling, etc.)

• Experience with end-to-end tools used to process multi-omic data from raw data all the way to analytical outputs. Good working knowledge of workflow managers (e.g., Flyte, Nextflow, Seqera, Snakemake).

• Operational software engineering skills: the ability to write high-quality code to be the backbone of our software stack.

• Strong working knowledge with cloud computing environments, including but not limited to AWS and GCP.

• Knowledge of GPU/CPU computing backbone, whether directly through GPU/CPU-accelerated bioinformatics (e.g., NVIDIA Parabricks, Clara, Rapids, etc.) or through the ability to identify GPU vs. CPU optimisation in other contexts.

• Familiar with data wrangling, engineering, analysis, and visualisation libraries using Python or Julia, Spark, Hadoop, NoSQL.

Based onsite in San Francisco, US or London, UK. We support O1 (US) and GTV (UK) visa applications.

Prima Mente is a place where great people get to tackle great challenges together. We’re innately curious, fundamentally hands on and passionate about excellence.

Together we build an environment where outstanding communication, scientific rigour and creative innovation come together to effect impact at pace.

Come build the world's frontier AI biology lab with us.

We arrange our lives so we can work in person as much as possible.