AI/Data Engineer – Data Infrastructure

About The Role TileBio is building a foundation model of pathology. We treat histology as a language of tissue and train models directly on raw, unlabelled whole slide images (WSIs) to learn the underlying structure of biology. Our system converts tissue into a sequence of learned tokens and trains transformer models to understand disease at scale. Data is our lifeblood, and we are looking for a Data Engineer to build the refinery. At TileBio, "Data Engineering" isn't just about moving rows in a database; it’s about architecting the flow of terabytes of high-resolution medical imagery. You will build and maintain the infrastructure that fuels our foundation model training. You will own the lifecycle of a Whole Slide Image from the moment it leaves a scanner or a partner’s server to the moment it becomes a versioned, reproducible training set for our AI team. What You'll Do Architect the ingestion and preprocessing of massive histopathology datasets (SVS, NDPI, iSyntax) Build and refine automated, high-throughput pipelines for tiling, filtering, and metadata extraction Implement rigorous dataset versioning so every training experiment is traceable and repeatable Coordinate data movement between local high-performance storage, cluster environments (SLURM), and cloud buckets Monitor and resolve quality issues, ensuring our models learn from the highest quality biological signals Work closely with Deep Learning Engineers to optimise data loading and throughput for multi-GPU training What We're Looking For Strong Python skills with the ability to write clean, performant, and maintainable code Hands-on experience managing large scientific, imaging, or unstructured datasets Experience with storage architectures such as ZFS, object storage, or cloud-native solutions Experience building and deploying automated data pipelines (e.g., Prefect, Dagster, Airflow, or custom-built) Deep understanding of data versioning (e.g., DVC, LakeFS) and why it matters for ML Nice to Have Experience with WSI formats or medical imaging libraries (OpenSlide, CuCIM) Experience with SLURM or other cluster-based scheduling systems Familiarity with Azure or AWS environments for hybrid-cloud workflows Strong systems thinking with the ability to design for "the next 100TB" today What We Offer Salary of £35,000 to £60,000 (depending on experience) and equity eligibility Opportunity to build the core infrastructure that enables biological discovery at a global scale A culture that optimises for impact, takes ownership, and delivers An environment that challenges ideas, not people, and values speed, clarity, and rigour To apply, email [email protected] with the subject "Data Engineer", your CV and a short note about why you're interested.