Posted On Apr 29

AI Frameworks Engineer


Location : Vancouver, BC

Headquarters : United States

Hiring Mode : Full Time

Experience : Mid Level

Vancouver, BC
Hybrid remote
  • Dental care
  • Employee stock purchase plan
  • Paid time off
Job Description
  • Intel is shaping the future of technology to help create a better future for the entire world. Our work in pushing forward fields like AI, analytics, and cloud-to-edge technology is at the heart of countless innovations. With a career at Intel, you’ll have the opportunity to use technology to power major breakthroughs—such as self-driving cars and rebuilding coral reefs—and create enhancements that improve our everyday quality of life.
  • Join us and help make the future more wonderful for everyone.
  • Intel's Visions Processing Unit (VPU) is a high-performance, low-power edge AI inference engine, used in a wide variety of mobile and IoT AI products.
  • The VPU Software Ecosystem team is looking for smart, passionate engineers at many levels to work with us on enabling VPUs in a wide variety of Machine Learning and Deep Learning ecosystems. The focus of the role is on prototyping, designing, implementing, and maintaining the different parts of the software stacks that make up these ecosystems. We want seasoned C/C++ engineers with experience working in large and complex codebases, and a passion for creating high-quality systems. Our components span Linux and Windows applications, libraries, compilers, kernel and user mode drivers, and embedded RTOS systems.
As an AI Frameworks Engineer you will:
  • Design, develop, and optimize VPU integrations with different AI frameworks such as WinML, ONNX, OpenVINO, Tensorflow, PyTorch, and NNAPI.
  • Identify and implement latency, throughput, and power optimizations for ML inference workloads.
  • Work and collaborate with other AI focused teams at Intel, our partners, and customers in finding solutions and enhancements for the VPU at a product level.
  • You must possess the below minimum education requirements and minimum required qualifications to be initially considered for this position. Additional preferred qualifications are in addition to the minimum requirements and are considered a plus factor in identifying top candidates.
Minimum Qualifications:
  • Bachelor’s in Computer Science or related field with 3+ years of experience in software industry.
  • Software design and coding skills in C/C++.
  • Problem solving and debugging skills, including postmortem debugging.
Preferred Qualifications:
  • Deploying Inference models on frameworks such as: ONNX runtime, TF, CoreML, WinML.
  • Development of modern compilers, especially with LLVM and MLIR.
  • Performance analysis and optimization, particularly in machine-learning.
  • Windows or Linux system programming experience.
  • Low-level device programming experience.
  • This position may be offered as virtual or onsite depending on location.
Benefits Statement:
  • Here at Intel, we invest in our people. Beyond health, dental, and retirement benefits, Intel’s benefits package includes 14 paid holidays per calendar year, three weeks of paid vacation, four-week paid sabbatical every four years of employment, family planning care including adoption and fertility assistance, and over 45 diverse employee resource groups for networking and advocacy. Intel also offers employees five bonuses per year dependent on overall company and personal performance, and an employee stock purchase program.
Inside this Business Group
  • The Internet of Things Group (IOTG) consists of ~4700 dedicated employees across 25 locations across the world. IOTG drives significant growth in the Internet of Things (IoT) market, capitalizing on the inflection and creation of edge computing, leveraging smart, connected devices and artificial intelligence (AI) to enable partners to transform their businesses. IOTG's vision is to lead the industry and enterprises to enhance the way we live and work by making it easier to create exciting, new IoT/edge solutions. IOTG's strategy includes creating unique differentiated silicon to consolidate workloads at the Edge, investing in video and AI inference as the killer app for the Edge, creating new developer tools and ecosystems, and establishing a dedicated vertical consultative sales team to add value to our partners across many verticals.
Work Model for this Role
  • This role will be eligible for our hybrid work model which allows employees to split their time between working on-site at their assigned Intel site and off-site.
  • Intel is committed to a culture of accessibility. Intel provides accommodations to applicants and employees with disabilities. Find information and request accommodation here