CV
Education
- Ph.D. in Computer Science, Télécom Paris, Polytechnic Institute of Paris, 2022
- Topic: Personalized Audio Auto-Tagging as Proxy for Contextual Music Recommendation
- Supervisors: Dr. Gaël Richard, Dr. Geoffroy Peeters, Dr. Elena V. Epure
- M.Sc. in Computer Science, National University of Singapore, 2018
- Topic: Recommending Music for Language Learning: The Problem of Singing Voice Intelligibility
- Supervisor: Dr. Ye Wang
- M.Sc. in Software Engineering, Nile University, 2016
- Topic: Primary-Ambient Separation of Audio Signals
- Award: Best Thesis Award
- Supervisors: Dr. Mahmoud Allam, Dr. Stefan Uhlich
- B.Sc. in Electronics Engineering, Fayoum University, 2014
Work experience
- May 2025 – Present: Senior Audio Research Scientist
- Serato, Auckland, New Zealand
- Lead R&D for next-gen beat detection and low-latency stem separation powering Serato creator products (e.g., Serato DJ Pro, Serato Studio).
- Designed tempo-tracking pipeline robust to genre shifts, swing, and drift.
- Provide technical leadership across research and product; mentor junior scientists/engineers.
- June 2023 – October 2024: Research Scientist
- Emobot, Paris, France
- Led research on speech emotion recognition, increasing accuracy to 96%, impacting healthcare applications with real-time responsiveness.
- Supervised research interns and junior researchers, leading projects from inception to prototype development.
- June 2022 – June 2023: R&D Project Manager
- Arkamys, Paris, France
- Led research project on road noise cancellation for vehicles.
- Managed end-to-end audio/ML project lifecycles from planning and resourcing to delivery and production.
- October 2018 – January 2022: Research Scientist
- Deezer, Paris, France
- Developed and implemented contextual music recommendation models, improving recommendations used by 10 million users.
- Conducted large-scale data collection and analysis to create music auto-tagging models for varying listening moods.
- Supervisor: Dr. Elena V. Epure
- March 2018 – August 2018: Research Intern
- IBM, Singapore
- Designed and trained NLP-based question answering systems using Markov Logic Networks.
- December 2016 – September 2018: Research Assistant
- National University of Singapore, Singapore
- Built evaluation system for singing-voice intelligibility to support language-learning music recommendation research.
- August 2015 – February 2016: Research Intern
- Sony Stuttgart Technology Center, Stuttgart, Germany
- Developed algorithms for primary-ambient source separation for audio up-mixing.
- Developed the first neural network based solution for primary-ambient source separation.
- Supervisor: Dr. Stefan Uhlich
Publications
