Focus on speech AI technology research and development. Responsible for innovating cutting-edge speaker diarization ML models for the core speech analytics product, “Callinter”. Duties involve scoping business needs as ML problems, data preparation and analysis, model training, optimisation, testing and deployment.

Led the development of voice AI technology. Core focus on enabling text-free voice conversion by utilising any-to-any VC models. Full stack ML from data acquisition and processing to model implementation and production. Implementation of generative AI techniques such as GANs to drive speech model development.Attained the SciTech Challenge 2021 Cantonese ASR Best Performance Award and SciTech Challenge 2021 Open-group Challenge Runner-up.

Academic research as part of the CSLT research group at The University of Sheffield.Research involved using generative adversarial networks (GANs) for automatic speech recognition data augmentation.

- Student Demonstrator for the Department of Computer Science- Student Note Taker for the Disability and Dyslexia Support Service

- https://airizy.com- https://spidfier.com- https://benchwrite.com- https://matthardydrums.com

- Cloud Computing- Computer Vision and Natural Language Processing - Frontend Software Engineering - Backend Software Engineering- Agile methodology and frameworks such as Scrum