Xilinx develops highly flexible and adaptive processing platforms that enable rapid innovation across a variety of technologies - from the endpoint to the edge to the cloud. Xilinx is the inventor of the FPGA, hardware programmable SoCs and the ACAP (Adaptive Compute Acceleration Platform), designed to deliver the most dynamic processor technology in the industry and enable the adaptable, intelligent and connected world of the future in a multitude of markets including Data Center (Compute, Storage and Networking); Wireless/5G and Wired Communications; Automotive/ADAS; Emulation & Prototyping; Aerospace & Defense; Industrial Scientific & Medical, and others. Xilinx's core strengths simultaneously address major industry trends including the explosion of data, heterogeneous computing after Moore's Law, and the dawn of artificial intelligence (AI).
Our global team is growing and we are looking for bold, collaborative and creative people to help us lead the industry transformation to build an adaptable intelligent world. We believe that by embracing diverse ideas, striving for excellence in all that we do, and working together as a unified team, we can accomplish anything. Come do your best work and live your best life as part of the ONEXILINX team!
You will be part of an R&D team that develops high-performance AI inference accelerators. Xilinx’s unique reconfigurable platform enables the design of optimized domain specific architecture for a variety of Deep Learning Algorithms. The ideal candidate will have worked on new instruction set architectures which may include CPU, NPU, GPU, Domain Specific Architectures and other forms of compute.
You will work on projects critical to Xilinx's growth, with opportunities to move among various teams and projects. You are versatile, display leadership qualities and are enthusiastic about tackling new problems across the full-stack as we continue to push technology forward. Most of all, you are driven to find creative solutions where solutions may not exist yet.
• Develop optimizing compilers, code generators and runtime execution frameworks for AI accelerators for Deep Learning.
• Work on compiling an intermediate graph representation (IR) to target specific code and define the interfaces to runtime systems and libraries.
• Collaborate with members of the software framework teams and the hardware architecture teams to accelerate the next generation of deep learning software.
• You will work on integrating the backend in a variety of deep learning frameworks - Caffe2, PyTorch, MxNet/TVM, Tensorflow
• MS/Ph.D. degree in Computer Science with 2+ years of industry experience or BA/BS degree in Computer Science with 5+ years of industry experience
• Passion for developing and optimizing compilers for modern architectures
• Working knowledge of compiler architecture, front-end and middle-end optimizations, scheduling, register allocation, back-end code generation
• High-level C++ programming expertise
• A solid foundation in data structures, computer arithmetic, algorithms and software design with strong analytical and debugging skills
• Excellent communication and collaboration skills
• Experience with the internals of one or more frameworks: Caffe2, PyTorch, MxNet or Tensorflow
• Experience with neural networks inference on dedicated SOC
• Research experience in developing compiler flow for custom processor architectures