We’re seeking talented engineers to develop leading-edge technology for hardware acceleration of AI & machine learning running millions of inferences every second in data centers around the world.

Brainwave is Microsoft’s architecture for accelerating deep neural network (DNN) inference using FPGAs.  The Brainwave system includes a high-performance distributed software runtime that handles client inference requests, routing them and orchestrating their execution across large pools of CPUs and FPGAs to provide low latency, highly parallel, and resilient service.

We are looking for software developers who are interested in working in a dynamic production environment, developing support for and deploying the latest DNN models to production in support of Bing, Office 365, and other Microsoft online services. Working with Microsoft model developers to deploy their models on Brainwave gives us the unusual opportunity of working across the whole DNN stack, from cutting-edge DNN models, techniques, and frameworks to hardware accelerator interfacing and architecture. This cutting-edge development takes place in the context of a live, global-scale distributed system that touches millions of users daily, running on the world’s largest distributed FPGA-accelerated hardware platform.

Responsibilities

Design, develop, deploy, and maintain a distributed software and hardware system for online serving of hardware-accelerated deep learning models.
Develop custom implementations of deep learning system components including software, compiler, firmware, quantization, and fine-tuning.
Gather data and provide insights on service and process usage.
Deploy our own tools on Azure-based and proprietary technologies.

Qualifications

Required Qualifications:

• 5+ years experience in programming languages such as C/C++/C# or Masters or PhD with 2+ years of relevant experience
• Demonstrated experience writing efficient multi-threaded and concurrent code
• Experience using agile software development technologies; ability to write clean, maintainable and tested code 

Preferred Qualifications:

• Ability to work with geographically dispersed teams in a fast-paced environmentExcellent written and communication skills
• Solid understanding of processor architecture and experience with embedded and/or assembly programming
• Familiarity with Machine Learning Frameworks such as Pytorch/Tensorflow
• Knowledge of both Windows and Linux operating systems
• Understanding of Internet protocols, Internet services and standards
• Experience in performance analysis and optimization of complex systems Finish
• Working on distributed infrastructure, shipping service-based applications 

Microsoft is an equal opportunity employer. All qualified applicants will receive consideration for employment without regard to age, ancestry, color, family or medical care leave, gender identity or expression, genetic information, marital status, medical condition, national origin, physical or mental disability, political affiliation, protected veteran status, race, religion, sex (including pregnancy), sexual orientation, or any other characteristic protected by applicable laws, regulations and ordinances.  We also consider qualified applicants regardless of criminal histories, consistent with legal requirements. If you need assistance and/or a reasonable accommodation due to a disability during the application or the recruiting process, please send a request via the Accommodation request form.