Software Engineer

Microsoft's Deep Learning Platform team is at the forefront of AI infrastructure, managing thousands of production servers and handling millions of requests per second. We're expanding our deep learning vector databases service to serve growing demands in web search and copilot features. The role involves working with cutting-edge technology, including ONNX, PyTorch, Kubernetes, and various CPU/GPU optimizations. You'll collaborate with Microsoft Research, focusing on performance analysis, scaling, distributed system debugging, and algorithm development. The position offers exposure to large-scale production systems and innovative AI technology, making it ideal for those interested in high-performance computing and distributed systems. The team emphasizes a growth mindset and collaborative environment, working on projects that directly impact Microsoft's AI capabilities. This role provides an opportunity to work with advanced vector search algorithms, optimize deep learning model kernels, and build scalable distributed systems.