United Kingdom
Doctor with 13 years’ NHS experience across Trauma & Orthopaedics, Urgent Care and latterly Oral and Maxillofacial Surgery (OMFS). I turn complex Healthtech issues into improved patient outcomes, improved patient safety and smoother services: from VR-assisted surgical education to AI-driven analytics and pragmatic quality improvement. Recent highlights: designed and ran a 2×2 feasibility/pilot RCT on VR-assisted teaching (Imperial/VRiMS), built analytics in Python/R to validate immersion & interactivity measures, and presented findings nationally (ASiT 2025). Clinically, I’ve led busy MIU shifts, taught PAs/ACPs/GPs, tightened clinical governance through participation in QI projects and GIRFT projects, and used Six Sigma tools to capture data and effect improvements in the triaging and management of patients with isolated dental trauma and the interrogation and remittance of OMFS-related case notes data on EHRs from Urgent Care to the OMFS team. I write and speak about surgical education, digital health, and service design — with publications in BJS, FDS and BMJ. If you’re building HealthTech (XR, AI/ML, SaMD) or modernising clinical education and pathways, let’s talk. French: J'ai appris le français et l'allemand à l'école et je maîtrise également les deux langues à un niveau intermédiaire. German: Ich habe in der Schule Französisch und Deutsch gelernt und obwohl ich keines der beiden Sprachen fließend spreche, versichere ich Ihnen, dass ich beide Sprachen auf mittlerem Niveau beherrsche.
Helping train large language models by applying domain expertise in Medicine and Healthcare in general.
Designed, reviewed, and annotated complex clinical datasets for training and validation of AI models (LLMs and NLP pipelines) in medical reasoning and diagnostics. Developed detailed evaluation rubrics for medical dialogue quality, factual accuracy, and empathy used as a “reward system” for reinforcement learning from human feedback (RLHF). Testing LLMs to failure.
Designed, reviewed, and annotated complex clinical datasets for training and validation of AI models (LLMs and NLP pipelines) in medical reasoning and diagnostics. Developed detailed evaluation rubrics for medical dialogue quality, factual accuracy, and empathy used as a “reward system” for reinforcement learning from human feedback (RLHF). Previously enrolled on projects via Outlier and Mercor.
- Designed, reviewed, and annotated complex clinical datasets for training and validation of AI models (LLMs and NLP pipelines) in medical reasoning and diagnostics. - Collaborated with interdisciplinary teams to refine model outputs and clinical consistency - Developed detailed evaluation rubrics for medical dialogue quality, factual accuracy, and empathy used as a “reward system” for reinforcement learning from human feedback (RLHF). - Using prompt engineering to build prompts and then stress-test LLMs to failure using techniques like CTTA (Chain-of-Thought Transfer Adversarial Attack) and evaluating the fidelity of outputs. - Enrolled on projects via Outlier, Mercor and micro1. - Completed DCB0129 and DCB0160 training for evaluation of Software as Medical Devices (SaMDs) and Artificial Intelligence as Medical Devices (AIaMDs). - Cognisant of ISO 14155 (Standards for clinical investigations of medical devices in humans), ISO 13485 (Standards for the regulatory compliance of medical devices), and ISO 14971 (Standards for risk management of Medical Devices).
- Minor Injuries Doctor within a Partnership for East London Consortium Urgent Care Centre - Daily governance to keep missed radiologic findings <2%; regular teaching for PAs/ACPs/GPs. - Development of healthcare systems, and trauma prevention in LMICs - Disaster Medicine Consultation - Expedition Medicine - Notarisation/Certification of copies of legal documents