London-based Head of AI - Surgical Imaging & Real-Time ML

Dex; Greater London; On-site; GBP 120,000 - 180,000; Full time

Job summary

Dex partners with a surgical AI company to lead the AI pillar end-to-end, building a team from the ground up to ship production AI for neurosurgery.

You will architect data pipelines for kinematics and tissue data, own the federated learning stack with NVIDIA FLARE, and collaborate on sim-to-real with Isaac Sim.

Delivery milestones include a neurosurgery anatomy recognition prototype by Q2 2028 with ≥85% accuracy and advancing from CV to vision-language-action for device automation.

Qualifications

• Shipped production AI/ML models in CV or related fields.
• Experience with medical imaging (DICOM, MONAI) or quick ramp.
• Ability to meet sub-20ms latency for edge deployment and manage DGX/RTX infra.
• Federated learning experience is a plus.

Responsibilities

• Deliver a working anatomy recognition prototype for neurosurgery by Q2 2028 with ≥85% segmentation accuracy.
• Lead the surgical foundation model program: CV to vision-language to vision-language-action.
• Architect data pipeline for kinematics and tissue-interaction data across endpoints.
• Own the federated learning stack and deploy NVIDIA FLARE.
• Define boundary with the simulation team on Isaac Sim, synthetic data, and sim-to-real transfer.

Skills

Production AI

Computer vision

Edge deployment

Federated learning

Team leadership

Tools

NVIDIA FLARE

Isaac Sim

MONAI

DICOM

Job description

Dex partners with a surgical AI company to lead the AI pillar end-to-end, building a team from the ground up to ship production AI for neurosurgery.

You will architect data pipelines for kinematics and tissue data, own the federated learning stack with NVIDIA FLARE, and collaborate on sim-to-real with Isaac Sim.

Delivery milestones include a neurosurgery anatomy recognition prototype by Q2 2028 with ≥85% accuracy and advancing from CV to vision-language-action for device automation.