Azure Compute is responsible for building the next generation(s) of highly scalable datacenters that provide containers, virtual machines and bare metal services. Given the growth of our datacenters we are always investigating new hardware and software solutions to meet our scale and customer demand. The Azure New Technology (ANT) team is looking ahead at future Cloud technologies, both hardware and software, for enablement within our datacenters. This role focuses on cultivating new technologies for Rack Scale to reduce stranded resources (e.g. disk space or peripherals) by disaggregating monolithic compute nodes into pooled local storage or accelerators (GPUs/TPUs/FPGAs etc). A good example of what we do is device virtualization and emulation for economies of scale in our datacenters. This is a multi-year effort that consists of deep partnership engagements with multiple silicon companies, including collaborating on future hardware designs and software enablement. We are a very hands-on
We are looking for people who have a broad skillset, people who are willing to continuously learn new things, and people who are willing to jump in anywhere to help the project move forward. Specifically, we are looking for software and hardware engineers who can optimize workloads for future hardware designs, port workloads, create/run benchmarks, provide feedback to silicon partners, etc. What we can offer in return is a strong team that empowers you and challenges you to grow. We also offer you access to the latest hardware and software, often years ahead of the rest of the industry, and in
Basic Qualifications: 8 years of software and/or hardware development experience BS in computer science or engineering; PhD and MS preferred or equivalent years of work experience Preferred Areas of Expertise: OS (Windows/Linux) Kernel, device drivers, firmware, software debuggers Hardware subsystems, peripherals, and hardware debuggers Programming predominantly in C GPUs, TPUs, CAD, OpenCL, OpenGL, rCUDA, AI Deep Learning (e.g. CNTK, Caffe) Kernel memory management and programming MMU/SMMU/IOMMU C++, C#, CMD, PowerShell, Perl, Python Cloud distributed systems and services Ability to meet Microsoft,