Senior Edge Inference Optimization Engineer

Intel Corporation; Santa Clara, Northern (CA, KY); Hybrid; USD 217,000 - 361,000; Full time

Job summary

Intel is seeking an Sr. Inference Optimization Engineer to accelerate models on edge devices. You will optimize inference engines for constrained hardware, including profiling, KV cache tuning, batching, and quantization.

This role focuses on fast, efficient local AI with privacy and low latency. You will work across iGPU/CPU paths, improve engine startup, and contribute fixes to open-source engines. A strong background in C++, Python, and LLM inference is required, with hybrid on-site work in

Qualifications

• BS/MS in CS, EE, Math or related STEM field.
• 8+ years software development background.
• Strong in C++ and/or Python; comfortable reading systems-level code.
• Experience with LLM inference (attention, KV cache, decoding).
• Experience profiling and optimizing real performance problems (CPU or GPU).
• Linux, build systems, and low-level debugging expertise.

Responsibilities

• Profile and optimize local inference (llama.cpp-vulkan and vLLM) for latency, throughput, and memory on edge hardware.
• Tune KV cache, continuous batching, and scheduling for interactive workloads.
• Drive quantization strategy (GGUF / AWQ / GPTQ) and validate quality impact with the Post-Training team.
• Cut CPU overhead and improve engine startup, model load, and lifecycle management.
• Benchmark across hardware tiers and publish performance comparisons.
• Upstream fixes and patches to open-source engines where it helps us.

Skills

C++

Python

LLM inference

Profiling

Performance optimization

Education

BS/MS in CS, EE, Math

Tools

llama.cpp

vLLM

ggml

Job description

Intel is seeking an Sr. Inference Optimization Engineer to accelerate models on edge devices. You will optimize inference engines for constrained hardware, including profiling, KV cache tuning, batching, and quantization.

This role focuses on fast, efficient local AI with privacy and low latency. You will work across iGPU/CPU paths, improve engine startup, and contribute fixes to open-source engines. A strong background in C++, Python, and LLM inference is required, with hybrid on-site work in