AI Inference Optimization Engineer
About The Position
Quadric is hiring an AI Inference Optimization Engineer for its AI Application team. The role focuses on getting current AI models—including CNN perception models, LLMs, VLMs, and VLAs—running accurately and efficiently on Quadric’s General Purpose Neural Processing Unit (GPNPU). The engineer will analyze real workloads, profile performance, write and tune kernels, select quantization strategies, and develop repeatable model conversion and deployment tools and workflows. Quadric develops edge AI technology for automotive, industrial, robotics, and embedded systems. The company is based in downtown Burlingame, California. The stated success measures for the first 6–12 months include independently deploying five new models on GPNPU while meeting accuracy targets, delivering a 2x speedup on a model, and shipping a deployment or optimization tool used regularly by the team.
Requirements
- At least 3 years of experience in AI model deployment or kernel optimization.
- BS or MS in computer science, computer engineering, or a related field.
- Strong C/C++ and Python skills.
- Hands-on performance analysis experience, including profilers, roofline and bandwidth reasoning, and identifying compute versus memory bottlenecks.
- Hands-on experience with quantization, including PTQ/QAT and int8/int4, and debugging accuracy loss.
- Experience writing performance-critical kernels using technologies such as CUDA, Triton, OpenCL, SIMD intrinsics, or DSP.
- Fluency with AI coding agents such as Claude Code or Cursor, and interest in building agent-driven workflows for kernel and model bring-up.
Nice To Haves
- Hands-on experience in pruning and sparsification.
- Understanding of accelerator microarchitecture, including memory hierarchy and DMA.
- Understanding of fixed-point and numerical methods, including mixed precision.
- Understanding of compiler code generation and kernel scheduling.
Responsibilities
- Analyze and optimize performance on GPNPU.
- Deploy and profile models on GPNPU, including vision and perception models, LLMs, VLMs, and VLAs.
- Analyze model accuracy and select an appropriate quantization scheme.
- Write and tune kernels and optimize model compute graphs on GPNPU, balancing speed and accuracy.
- Create efficient workflows to convert and deploy models on GPNPU.
- Develop tools and workflows—including profiling, tracing, visualization, and agentic automation—to accelerate deployment and identify bottlenecks.
- Customize open-source model optimization and quantization tools.
- Integrate and automate model pruning, sparsification, and quantization in the workflow.
Benefits
- Medical, dental, and vision insurance from day one, with premiums covered at 99% for employees.
- Company-paid life insurance.
- Voluntary supplemental life insurance.
- Short-term and long-term disability insurance.
- Commuter support, including parking or Caltrain reimbursement.
- Flexible spending account (FSA) and health savings account (HSA).
- Equity.
- Paid parental leave.
- 401(k) retirement plan.
- Flexible PTO.
- Winter holiday shutdown.
- Catered lunch each day in the office.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Mid Level
