Shivam Mehta
Research Scientist - Gen AI at Netflix
Los Gatos, California, United States
Summary
🤩
Rockstar🎓
Top SchoolShivam Mehta is a research scientist and PhD candidate specializing in probabilistic machine learning for speech synthesis, currently applying generative AI at Netflix after research internships at Meta and Microsoft Research. With a decade of experience spanning academic research at KTH, Ghent, and ITMO, he bridges rigorous probabilistic modeling with practical system engineering from earlier Java/ETL and security roles. His recent work extends unimodal LLMs to multimodal audio understanding using novel discrete audio codebooks and contributed to an ICASSP paper, highlighting a knack for turning theoretical ideas into reproducible experiments. Based in Los Gatos, he combines deep academic training in applied mathematics with production-oriented productization of speech generative models, and maintains an active GitHub showcasing his research prototypes.
10 years of coding experience
2 years of employment as a software developer
Vivekanand SchoolDoctor of Philosophy - PhD Applied Mathematics, Doctor of Philosophy - PhD Applied Mathematics at KTH Royal Institute of TechnologyBachelor's Degree Computer Science, Bachelor's Degree Computer Science at Amity University, Greater Noida CampusResearch Natural Language Processing, Research Natural Language Processing at Ghent UniversityMasters Machine Learning And Data Analysis, Masters Machine Learning And Data Analysis at ITMO University
English, Swedish, Hindi, Russian
Github Skills (78)
mixing10
python10
diffusion-models10
mxnet10
text-to-speech10
voice-conversion10
deep-learning10
speech10
forecast10
variational-autoencoder10
freetts10
adversarial-learning10
ai10
paddlepaddle10
computer-vision10
Programming languages (6)
Github contributions (5)
shivammehta25/TTS
Nov 2022 - Oct 2023
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
Contributions:66 pushes, 3 branches in 10 months
deep-learningtext-to-speech
shivammehta25/diffusers
Mar 2023 - Sep 2023
🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch
Contributions:30 pushes, 3 branches in 5 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.