Q

Quadric

GPNPU hardware and software for ML

AI Inference Framework Engineer

AI Application EngineeringConfirmed live in the last 24 hours
Full-timeBurlingame, CA, USA

About the Job

Requirements

  • At least 3 years of experience building or extending machine learning frameworks or inference runtimes.
  • A Bachelor of Science or Master of Science in Computer Science, Computer Engineering, or a related field.
  • Strong C and C++ skills and Python skills.
  • A solid understanding of framework internals, including tensor memory management, graph scheduling, and operator dispatch.
  • A solid understanding of AI compute performance analysis and optimization.
  • Fluency with AI coding agents such as Claude Code and Cursor, and interest in building agent-driven workflows for backend and model bring-up.

Responsibilities

  • Integrate the GPNPU backend into AI compute frameworks such as llama.cpp, PyTorch, vLLM, and Optimum.
  • Implement framework backend interfaces, memory allocation, compute dispatch, registration, and operators or kernels.
  • Implement model compute pipelines including prefill, decode, batching, multi-sequence, and multi-modal processing.
  • Support framework serving features including KV-cache management, paged attention, continuous batching, and speculative decoding.
  • Optimize framework performance and accuracy for the GPNPU backend.
  • Reduce host-device dispatch overhead, implement graph capture and replay, integrate efficient kernels, and minimize latency.
  • Support quantization formats including GGUF (Q4/Q8), GPTQ/AWQ, int8, and fp16.
  • Validate accuracy against reference backends using perplexity and task benchmarks, and drive improvements.
  • Bring up a new LLM/VLM family end to end on the GPNPU backend with accuracy matching the reference.
  • Deliver measurable tokens-per-second or latency gains on a frontier model.
  • Ship a serving feature such as paged KV cache in a production release.

Desired Qualifications

  • Experience writing an accelerator backend, such as CUDA, Metal, Vulkan, Hexagon, or another NPU, for an open-source framework.
  • Contributions to open-source frameworks such as PyTorch, llama.cpp, or vLLM.
  • Understanding of low-level AI compute pipelines, CPU/NPU, and DMA.
  • Understanding of graph compilers and kernel fusion.

About the Company

Quadric

GPNPU hardware and software for ML

Quadric.io provides an integrated hardware-software platform for ML on System-on-Chips, centered on its Chimera General-Purpose Neural Processing Unit (GPNPU). Developers write ML code in C, which is compiled by the Chimera LLVM C Compiler, simulated with the Chimera Instruction Set Simulator (ISS), and deployed via a Software Development Kit (SDK) that supports design, profiling, and execution on Chimera. The solution is a single, end-to-end pipeline that eliminates the need to partition code across DSPs/GPUs and CPUs, offering tightly integrated hardware and software tools that can run a wide range of C-based neural-network operations. Quadric.io aims to simplify and accelerate the design of ML-enabled SoCs for semiconductor developers and manufacturers, enabling faster time-to-market and better ML performance through its cohesive hardware-software stack.

Company size
51-200
Company stage
Series C
Total funding
$94.3M
Headquarters
Burlingame, CA
Founded
2017

Recently Posted Jobs

Explore more opportunities at Quadric

See more jobs