India Engineering Head: Azureml Inferencing Team | Group Engineering Manager
CurrentMicrosoft’s bold vision of Azure Machine Learning (ML) is to democratize ML and make it available to every enterprise, developer and data scientist. I am leading a team which is entrusted with serving all internal and external ML workloads mounting to serving billions of requests per day on the most cutting-edge scenarios and models across the company. The inference team works on the next generation of model serving that includes hosting OAI models like ChatGPT, hosting models at Bing and Office scale and many exciting problems on the intersection of AI and Cloud. Designing and building highly reliable, available platform to support model inferencing at scale and work on high throughput/low latency scenarios and driving performance optimization capabilities.
