Summary
Sai Vinay is an audio machine learning engineer with eight years of experience building real-time, on-device speech and audio solutions for resource-constrained platforms. Currently at Google DSPA, he specializes in deploying efficient ML models for hearables and mobile devices, with deep hands-on expertise in Python, C/C++, Kaldi, TensorFlow and PyTorch. Previously he led R&D at Meeami, shipping lightweight speech enhancement, speaker verification and keyword spotting systems used in products like Jio Phone and integrations with Alexa and Siri, demonstrating strong end-to-end productionization skills. He combines signal-processing rigor with practical edge optimization—achieving high PESQ/MOS gains and low latency—while iterating from real-world user feedback. Trained at IIIT RGUKT, he’s passionate about translating cutting-edge research into robust, low-footprint deployments across embedded voice applications.
8 years of coding experience
4 years of employment as a software developer
Bachelor of Technology, Computer Science, Bachelor of Technology, Computer Science at IIIT RGUKT