Job Description

• Help implement customer processing pipelines that include Deep Neural Networks (DNNs), Large Multimodal Models (LMM) for audio and video applications.
• Architect, Design and Implement Audio and Video Processing functions (APIs) for ML applications using on chip vector DSP and ARM NEON processors.
• Design and implement Python reference processing modules.
• Design and implement Gstreamer algorithm plugins for applications.
• Measure accuracy and throughput of processing modules and optimize performance and accuracy to meet requirements.
• Work with chip hardware team to define next generation algorithmic compute blocks.

• BS/MS in Physics, Electrical Engineering or Computer Science with 15+ years of experience developing system software for complex vision, audio, image or video processing applications. 
• A strong knowledge of DSP, Image, Audio, Video, Computer Vision Algorithms and Frameworks is required, including common libraries like OpenCV and OpenCL. 
• Good programming skills in C, C++ and Python in a Linux environment. 
• Experience with DSPs, GPGPUs, SIMD or VLIW instruction sets such as ARM Neon, TI DSP, or any Vision processor like Cadence Tensilica, CEVA, RISC-V, Xilinx Versal, etc. is highly desirable. 
• Strong mathematical foundation in algorithms, DSP and deep learning is desired. 
• History of optimizing algorithms to align to HW platform capabilities, both for processing and memory transfer performance. 
• Experience with 2D and 3D DMA programming and performance tuning. 
• 2+ years of experience bringing up SoCs from scratch is a plus.