Rudrabha Mukhopadhyay
Co-Founder & CTO at sync. labs
Hyderabad, Sindh, United States
Summary
🤩
Rockstar🎓
Top SchoolRudrabha Mukhopadhyay is a Co-Founder and CTO with eight years of experience bridging cutting-edge research and product-grade AI, currently building controllable generative video models at Sync (Y Combinator W24, GV-backed). He completed a PhD in Computer Vision and Deep Learning at IIIT Hyderabad, where his research and engineering work—such as substantial contributions to the CVPR 2020 Lip2Wav project—focused on multimodal synthesis and robust training/inference pipelines. Comfortable moving models from lab to deployment, he has hands-on expertise in model training, preprocessing, and inference engineering that underpin real-world generative systems. Based in Hyderabad with an international outlook, he pairs academic rigor with startup grit to create AI that aims for measurable impact beyond academic benchmarks.
8 years of coding experience
W24, W24 at Y CombinatorBachelor of Technology, Computer Science, Bachelor of Technology, Computer Science at Heritage Institute of TechnologyDoctor of Philosophy - PhD, Computer Vision, Deep Learning, Doctor of Philosophy - PhD, Computer Vision, Deep Learning at IIIT Hyderabad
English, Bengali, Hindi
Stackoverflow
1reputation
130reached
0answers
1question
Github Skills (12)
computer-vision10
machine-learning10
audio-processing10
tensorflow10
trainings10
python10
modeling10
preprocess9
preprocessing9
hyperparameter-tuning9
opencv6
android6
Programming languages (3)
Github contributions (5)
Rudrabha/Lip2Wav
Apr 2020 - Sep 2020
This is the repository containing codes for our CVPR, 2020 paper titled "Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis"
Role in this project:
ML Engineer
ML EngineerContributions:57 commits, 1 PR, 37 pushes in 5 months
Contributions summary:Rudrabha primarily contributed to the training and synthesis aspects of the Lip2Wav project, modifying the `train.py` and `synthesizer` files. Their work included changes to hyperparameters, model initialization, loss and optimizer additions, and the training loop. They also worked on the preprocessing pipeline, including the correction of bugs and the addition of dataset-specific features. Furthermore, the user made changes to the inference code, indicating involvement in the model's deployment or testing.
speech-synthesis
Rudrabha/FriendBlend
Sep 2018 - May 2020
Contributions:64 commits, 54 pushes, 1 branch in 1 year 7 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.