Quadric has created an innovative general purpose neural processing unit (GPNPU) architecture. Quadric's co-optimized software and hardware is targeted to run neural network (NN) inference workloads in a wide variety of edge and endpoint devices, ranging from battery operated smart-sensor systems to high-performance automotive or autonomous vehicle systems. Unlike other NPUs or neural network accelerators in the industry today that can only accelerate a portion of a machine learning graph, the Quadric GPNPU executes both NN graph code and conventional C++ DSP and control code.
Role:The AI Applications Engineer is the key bridge between development engineering and hands-on users in the field. The AI Application Engineer will [1] integrate Quadric product and software stack into AI/LLM frameworks and ecosystem; [2] develop AI applications based on Quadric products; [3] lead technical customer/developer support initiatives in collaboration with field application engineers, Business Development, Product, and Engineering teams; and [4] develop technical materials to support the use of Quadric product. This position requires exceptional technical depth, strong coding capabilities, and advanced troubleshooting skills to develop AI applications, benchmarks, and reference implementations using Quadric's SDK. This senior technical role demands expertise in system architecture, AI frameworks, algorithm optimization, and the ability to provide technical leadership across global FAE teams. Candidates must demonstrate deep technical mastery of Quadric's product ecosystem including HPC Hardware (IP, Chips, Boards), SDK, and various algorithms (NN, DSP, Vision, Path Planning, etc.).
Responsibilities:- Customize AI/LLM frameworks and integrate Quadric products and SDK into AI/LLM ecosystem
- Develop AI applications, demos using Quadric's SDK and AI frameworks to showcase product capabilities and performance to developer community and customers
- Design and implement optimization strategies for AI/LLM applications on Quadric's platform
- Analyze complex AI/LLM application requirements/issues and architect optimal solutions leveraging Quadric's technology
- Provide technical leadership, training and support to developer community and customers worldwide
- Work with Business Development to articulate technical value propositions to potential customers
- Collaborate with Product and Engineering teams to influence product roadmap based on application needs
- Stay current with industry trends, competitive technologies, and emerging applications
- Occasional travel required to customer sites
Requirements
- Bachelor’s or Master's in Computer Science and/or Electronics Engineering field.
- 5+ years experience with AI/LLM frameworks in at least one of the following: PyTorch, vLLM, Tensorflow, onnxruntime, llamacpp; deep understanding of the framework's codebase
- Demonstrate knowledge of computer vision, perception, or LLM, and experience in related application development
- Proficiency in Python and C/C++, experience with CUDA, NEON a plus
- Experience with Linux, docker based development environments
- Experience with quantization and model accuracy analysis a plus
- Ability to methodically debug problems, relay information to the engineering team, and test and deploy system updates and upgrades.
Benefits
- Health Care Plan (Medical, Dental & Vision)
- Retirement Plan (401k, IRA)
- Life Insurance (Basic, Voluntary & AD&D)
- Paid Time Off (Vacation, Sick & Public Holidays)
- Family Leave (Maternity, Paternity)
- Short Term & Long Term Disability
- Training & Development
- Work From Home
- Free Food & Snacks
- Stock Option Plan
Top Skills
What We Do
Quadric has built a unified hardware/software architecture optimized for on-device machine learning inference. Only the Quadric GPNPU (general purpose neural processing unit) delivers high ML inference performance while also running C++ code without forcing the developer to artificially partition application code between two or three different kinds of processors. Quadric's GPNPU is a licensable processor IP core that scales from 1 to 64 TOPs and seamlessly intermixes scalar, vector and matrix code.
