Redmond, Washington, United States
I design, implement, and integrate advanced digital signal processing (DSP) algorithms and AI models to enhance real-time communication experiences, ensuring best-in-class audio quality across diverse networks and devices.
With a deep understanding of signal processing, data analysis, and software architecture, I contribute to cutting-edge solutions that power platforms like Microsoft Teams, Microsoft Mesh, M365 Copilot voice mode, PSTN cloud, and Azure Communication Services. I write efficient, scalable, and extensible code while leveraging statistical insights to drive performance improvements.
I have also contributed to different stages of the training, integration, and deployment of AI models for real-time audio processing: noise suppression, echo cancellation, and packet loss concealment.
Some of the most impactful projects I have worked on are about bringing the top audio features from Teams desktop to the web platform using modern technologies like WebAssembly, and to the cloud platform for PSTN endpoints. For the PSTN scenario, my work to implement AI-based noise suppression helped reduced the volume of monthly noise reports by 75%.