AI Inference Framework Engineer

What you'll do

• Build framework backend interfaces, memory allocation, compute dispatch, registrations, and operators/kernels; implement model compute pipelines and serving features.
• Optimize performance and accuracy, including dispatch overhead, graph capture/replay, kernels, quantization, and validation against reference backends.
• Work with kernel, runtime, and compiler teams to bring model families to the GPNPU backend and deliver serving features.

What they ask for

• 3+ years building or extending ML frameworks or inference runtimes.
• BS/MS in CS/CE or related fields.
• Strong C/C++ and Python.
• Understanding of framework internals and AI compute performance analysis and optimization; fluent with AI coding agents.

Nice to have

• Experience writing an accelerator backend for an open-source framework; contributions to PyTorch, llama.cpp, or vLLM.
• Understanding of low-level AI compute pipelines, CPU/NPU, DMA, graph compilers, and kernel fusion.

Pay

$160,000 to $195,000 USD base salary

Tools

GPNPU, llama.cpp, PyTorch, vLLM, Optimum, C/C++, Python, GGUF

AI focus

Develop and optimize neural-network and LLM/VLM inference on Quadric’s GPNPU, including framework integration, serving features, quantization, and AI coding-agent workflows.