Tornike Karchkhadze
Audio AI Research Scientist Intern at UC San Diego
San Diego, California, United States
Summary
🤩
Rockstar🎓
Top SchoolTornike Karchkhadze is an audio machine learning researcher and Computer Music Ph.D. candidate at UC San Diego with over 15 years of experience spanning music composition, sound design, and data science. He builds and scales generative audio systems—using diffusion models, transformers, VAEs and GANs—for tasks from text-driven Foley synthesis to multitrack music generation, and currently researches co-creativity in the REACH project in collaboration with IRCAM. Tornike has industry experience advancing production-ready models at Bose and Apple internships, and practical engineering chops in large-scale dataset pipelines and PyTorch/TensorFlow implementations. Beyond research, he teaches undergraduates, develops custom audio plugins and MAX/MSP tools, and has a track record of adapting ML to niche problems like Georgian speech recognition and personalized HRTFs. His background uniquely combines formal physics and finance training with deep musical practice, enabling a rare blend of rigorous modeling and artistic sensibility.
6 years of coding experience
11 years of employment as a software developer
Bachelor's degree, Music Technology, Bachelor's degree, Music Technology at Sibelius-Akatemia - Sibelius-AkademinBachelor's degree, Music Technology, Bachelor's degree, Music Technology at Tbilisi state ConservatoireKomarovi Campus SchoolMaster's degree, Accounting and Finance, Master's degree, Accounting and Finance at Caucasus UniversityBachelor's degree, Physics, Bachelor's degree, Physics at Tbilisi State UniversityUniversity of California, San DiegoMaster's degree, Sonology, Master's degree, Sonology at Koninklijk Conservatorium - Royal Conservatoire
English, Russian, Georgian
Stackoverflow
928reputation
47kreached
44answers
15questions
tensorflow
top-5%
Github Skills (191)
transformers10
language-model10
mass10
python10
deep-learning10
gpu10
cudnn10
nvrtc10
cusparse10
cublas10
mass-spectrometry10
numpy10
trinitycore10
azerothcore10
ai10
Programming languages (12)
Github contributions (5)
tornikeo/tornikeo
Nov 2020 - Jan 2025
Contributions:16 pushes, 1 branch in 4 years 2 months
tornikeo/matchms
Jan 2024 - Mar 2025
Python library for processing (tandem) mass spectrometry data and for computing spectral similarities.
Contributions:31 pushes, 19 branches in 1 year 2 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.