Join a team of engineers, surgeons, and scientists developing vision systems that protect patients in the operating room and advance cell & gene therapy manufacturing.
📍 Cambridge, UK💼 Full-Time or Internship🧠 Computer Vision & Deep Learning👥 Reports to CEO
Own and improve the core vision pipeline that identifies surgical instruments being packed into trays. Work across the full ML lifecycle: data preparation, model training, evaluation, deployment, and monitoring.
Key Responsibilities
Improve instrument identification accuracy across diverse tray configurations and lighting conditions
Reduce inference latency for real-time feedback during the packing workflow
Build robustness against edge cases: reflective surfaces, overlapping instruments, partial occlusions, and variable wear
Develop and maintain the data pipeline (annotation, augmentation, model retraining)
Collaborate with the clinical team to translate SPD workflow requirements into technical specifications
Contribute to expanding platform capabilities: instrument condition assessment, tray completeness verification, and hospital inventory integration
Essential Requirements
Strong foundation in computer vision and deep learning (object detection, instance segmentation, image classification)
Hands-on experience with PyTorch or TensorFlow and modern vision architectures (YOLO, Detectron2, Vision Transformers, or similar)
Proficiency in Python; comfort with Git and collaborative development
Ability to work across the full ML lifecycle: data preparation, model training, evaluation, deployment, and monitoring
Genuine interest in building systems that work reliably in the real world, not just on benchmarks
Highly Valued
Experience with edge deployment and model optimisation (ONNX, TensorRT, quantisation)
Background in fine-grained visual recognition, metallic/reflective object detection, or industrial inspection
Familiarity with camera systems, lighting setups, and physical constraints of real-world vision deployments
Experience with MLOps tooling (experiment tracking, data versioning, CI/CD for ML)
Published research or a Master's/PhD project in a relevant area
Internship Track
Structured 3-month paid internship with a clear conversion path to a full-time role
Designed around a concrete deliverable — for example, improving instrument segmentation robustness under variable SPD lighting
Suited to final-year undergraduates, Master's students, or recent graduates looking for high-ownership roles
📍 Babraham Research Campus, Cambridge, UK💼 Full-Time or Contract🧬 Stem Cell Biology & CGT👥 Reports to CSO
Build a new stem cell platform from the ground up within a growing CGT company. Work at the cutting edge of AI + automation + cell therapy manufacturing, based at Babraham Research Campus.
Key Responsibilities
Establish and optimise iPSC culture workflows, including surface coating strategies (e.g. Matrigel, vitronectin, synthetic matrices) and scale-up approaches compatible with roller bottle and automated systems
Develop and evaluate organoid and 3D culture systems, including feasibility within closed or semi-automated platforms
Design and implement AI-assisted imaging workflows for real-time quality control of iPSC colony morphology, differentiation efficiency, and organoid formation and maturity
Build and curate a proprietary cell imaging dataset ("cell atlas") to support machine learning model development
Develop directed differentiation protocols for iPSC-derived cell types relevant to CGT and allogeneic cell therapy applications
Collaborate with engineering and data science teams to integrate biological workflows into the Bodhi platform
Contribute to grant applications, technical reports, and publications, supporting funding efforts (e.g. Innovate UK, UKRI)
Essential Requirements
PhD (or equivalent experience) in stem cell biology, regenerative medicine, CGT, or related field
Strong hands-on experience with iPSC & MSC culture and maintenance
Experience with stem cell QC characterisation, passaging, and differentiation workflows
Experience with adherent cell culture scale-up (e.g. coated surfaces, multilayer systems, microcarriers, or bioreactors)
Proven ability to design, execute, and troubleshoot experiments independently
Experience with cell imaging techniques (brightfield, phase contrast, fluorescence microscopy)
Strong analytical mindset and data-driven approach to experimental optimisation
Interest in applying AI / computational methods to biological systems
Highly Valued
Experience with 3D culture systems (organoids, spheroids, extracellular matrix-based systems)
Expertise in iPSC differentiation into therapeutically relevant lineages (e.g. neural, cardiac, hepatic, immune)
Familiarity with automated or semi-automated culture platforms (bioreactors, liquid handlers, robotics)
Experience with image-based assays and quantitative image analysis (e.g. CellProfiler, FIJI/ImageJ)
Programming skills (Python, R, MATLAB) for data analysis or image processing
Track record of peer-reviewed publications in stem cell biology, organoids, or CGT