Sr. Inference Optimization Engineer (local / edge runtime)

PVH (Tommy Hilfiger/Calvin Klein); Santa Clara (CA); On-site; USD 180,000 - 240,000; Full time

Benefits offered by this job

Intel Benefits

Job summary

Intel is seeking a seasoned software engineer to accelerate AI inference on edge hardware. You will optimize llama.cpp/vLLM, tune KV cache, batching and scheduling, and push quantization strategies to balance speed and quality.

This role focuses on low-latency, privacy-preserving AI workloads run on client devices. You will work across hardware tiers, benchmark performance, and contribute upstream fixes to open-source engines, helping deliver safe, efficient AI at scale while maintaining energy

Qualifications

• BS/MS in CS/EE/Math or related STEM field.
• 8+ years software development background.
• Strong in C++ and/or Python; reading systems-level code.
• Experience with LLM inference and KV cache.

Responsibilities

• Profile and optimize local inference for latency and throughput on edge hardware.
• Tune KV cache, batching, and scheduling for interactive workloads.
• Drive quantization strategy and validate quality impact.
• Cut CPU overhead and improve engine startup, model load, and lifecycle.
• Benchmark across hardware tiers and publish honest performance comparisons.
• Upstream fixes and patches to open-source engines where it helps us

Skills

C++

Python

LLM inference

Linux

Profiling

Optimization

Education

BS/MS in CS/EE/Math or related STEM field

Tools

llama.cpp

vLLM

ggml

CUDA

Job description

Job Details:

Job Description

Our MissionAt Intel, our journey is to transform AI into something safer, more trustworthy, and respectful of human privacy by design. We believe transformative AI should have a positive impact on people-powerful in capability, yet honest about its limits and protective of the data and resources it touches.To get there, we build agentic AI that combines the best of local and cloud intelligence - private, affordable, and sustainable by design. Small, efficient models run directly on the user's machine (AI PC, edge, on-prem, and beyond), keeping data private and token costs low, while powerful cloud models handle the hardest work: planning, reasoning, and complex problem-solving. Today, neither approach can deliver this alone. Together, they give people real capability without compromise-data stays private, spend stays predictable, and energy use stays in check.We're building intelligence that scales without sacrificing trust, cost, or the planet-because the future of AI should belong to the people it serves

Role Summary

Make models fast on the hardware people actually own. You optimize inference engines (llama.cpp, vLLM) for constrained local and edge environments - GPU/iGPUs, Vulkan backends - not datacenter H100 environment, mostly PC/edge. KV cache, batching, quantization, scheduling, and CPU-overhead reduction are your daily tools.This is the rare skill that makes a hybrid, low-cost agent product viable.

What you’ll do

• 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 agent 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 (start / stop / health)
• Benchmark across hardware tiers and publish honest performance comparisons
• Upstream fixes and patches to open-source engines where it helps us

What you’ll learn / grow into

• The internals of modern inference engines and where the milliseconds actually go
• Hardware‑aware optimization across iGPU / CPU paths (Vulkan, SYCL, oneAPI, CUDA where relevant)
• The quality-vs-speed-vs-memory trade space for small models
• Interest in local / edge AI and squeezing hardware

Qualifications

Minimum qualifications are required to be initially considered for this position. Preferred qualifications are in addition to the minimum requirements and are considered a plus factor in identifying top candidates.You must possess the minimum qualifications to be initially considered for this position. Preferred qualifications are in addition to the minimum requirements and are considered a plus factor in identifying top candidates.

Required 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) and can prove the speedup
• Linux, build systems, and low-level debugging expertise

Preferred Qualifications

• Hands‑on with llama.cpp, vLLM, ggml, or similar engines
• Experience with GPU / accelerator programming (Vulkan, CUDA, SYCL, Metal) or SIMD / CPU kernels
• Familiarity with quantization formats and their quality trade‑offs
• Open‑source contributions to inference engines

Benefits at Intel

Our total rewards package goes above and beyond just a paycheck. Whether you're looking to build your career, improve your health, or protect your wealth, we offer generous benefits to help you achieve your goals. Go to Intel Benefits | Intel Careers for details of benefits available to you. Intel reserves the right to modify, change or discontinue benefit plans at any time in its sole discretion.

Job Type

Shift:Shift 1 (United States of America)

Primary Location

US, California, Santa Clara

Additional Locations

US, Arizona, Phoenix, US, California, Folsom, US, Oregon, Hillsboro

Posting Statement

All qualified applicants will receive consideration for employment without regard to race, color, religion, religious creed, sex, national origin, ancestry, age, physical or mental disability, medical condition, genetic information, military and veteran