GPNPU AI Backend Engineer for Edge Inference

quadric

Burlingame (CA)

On-site

USD 160,000 - 195,000

Full time

14 days+

A complete application in a minute

Tailored resume and cover letter, ready to send.

Get past ATS filters

Benefits offered by this job

Medical, dental, and vision insurance
Company-paid life Insurance
401(k) Retirement Plan
Flexible PTO
Parental Leave
Catered lunch

Job summary

Quadric is redefining edge AI with the industry's first GPNPU. A member of our AI Application team, you will integrate the GPNPU backend into frameworks developers already use, enabling customers to move applications from GPUs with minimal changes.

You will own backend integration from memory and dispatch through serving features, collaborating with kernel, runtime and compiler teams. Responsible for optimizing performance/accuracy, reducing host-device dispatch, and supporting quantization

Qualifications

  • 3+ years building or extending ML frameworks or inference runtimes.
  • BS/MS in CS/CE or related fields.
  • Strong C/C++ and Python.
  • Solid understanding of framework internals: tensor memory management, graph scheduling, operator dispatch.
  • Solid understanding of AI compute performance analysis and optimization.
  • Experience writing an accelerator backend for an open-source framework.
  • Contribution to open-source frameworks (PyTorch, llama.cpp, vLLM).
  • Understanding of CPU/NPU, DMA, graph compilers and kernel fusion.

Responsibilities

  • Integrate GPNPU backend into AI compute frameworks (llama.cpp, PyTorch, vLLM, Optimum).
  • Implement framework backend interface, memory allocation, compute dispatch, registration and operators/kernels.
  • Implement model compute pipelines including prefill, decode, batching, multi-sequence and multi-modal.
  • Support serving features including KV-cache management, paged attention, continuous batching, speculative decoding.
  • Optimize framework performance and accuracy for GPNPU backend.

Skills

ML frameworks
C/C++
Python
AI compute perf analysis
Accelerator backend
Open-source contributions
Graph compilers
Kernel fusion

Education

BS/MS in CS/CE

Tools

CUDA
Metal
Vulkan
Hexagon

Job description

Quadric is redefining edge AI with the industry's first GPNPU. A member of our AI Application team, you will integrate the GPNPU backend into frameworks developers already use, enabling customers to move applications from GPUs with minimal changes.

You will own backend integration from memory and dispatch through serving features, collaborating with kernel, runtime and compiler teams. Responsible for optimizing performance/accuracy, reducing host-device dispatch, and supporting quantization

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Edge AI Inference Framework Engineer (GPNPU)
Edge AI Inference Framework Engineer (GPNPU)

QUADRIC PTY LTD • Burlingame (CA)

On-site
USD 160,000 - 195,000
Medical, dental, and vision insurance
401(k) with matching
Equity in the company
+5
Edge AI Inference Optimization Engineer on GPNPU (Equity)
Edge AI Inference Optimization Engineer on GPNPU (Equity)

QUADRIC PTY LTD • Burlingame (CA)

On-site
USD 160,000 - 195,000
Medical, dental, and vision insurance
Equity in the company
401(k) Retirement Plan
+3
Edge AI Inference Performance Engineer
Edge AI Inference Performance Engineer

quadric • Burlingame (CA)

On-site
USD 160,000 - 195,000
Medical, dental, vision insurance
Equity
401(k)
+6
AI Inference Backend Engineer - Cross-Framework Integration
AI Inference Backend Engineer - Cross-Framework Integration

Semiengineering • Burlingame (CA)

On-site
USD 130,000 - 170,000
AI Inference Framework Engineer Quadric
AI Inference Framework Engineer Quadric

Semiengineering • Burlingame (CA)

On-site
USD 130,000 - 170,000
Staff Deep Learning Compiler Engineer Quadric
Staff Deep Learning Compiler Engineer Quadric

Semiengineering • United States

Remote
USD 140,000 - 230,000
Edge AI Deep Learning Compiler Engineer
Edge AI Deep Learning Compiler Engineer

Semiengineering • United States

Remote
USD 140,000 - 230,000
Edge AI Kernel Intern: Optimize Inference on a GPNPU
Edge AI Kernel Intern: Optimize Inference on a GPNPU

quadric • Burlingame (CA)

On-site
USD 69,000 - 79,000
Catered lunch
Downtown Burlingame office
Work culture focused on innovation
+1
Edge AI Systems Software Engineer - Toolchains & Debugger
Edge AI Systems Software Engineer - Toolchains & Debugger

QUADRIC PTY LTD • Burlingame (CA)

On-site
USD 150,000 - 220,000
Medical, dental, and vision insurance
Equity
401(k) Retirement Plan
+2
Senior Edge AI Hardware Architect & RTL Lead
Senior Edge AI Hardware Architect & RTL Lead

QUADRIC PTY LTD • Burlingame (CA)

On-site
USD 150,000 - 220,000
Medical, dental, and vision insurance
Company-paid life Insurance
Par parental leave
+3