<h1>Inference Optimization Engineer (local / edge runtime)</h1><p><strong>Location:</strong> US, California, Santa Clara, US, Oregon, Hillsboro, US, California, Folsom, US, Arizona, Phoenix</p><p><strong>Time Type:</strong> Full time</p><h3>Job Description</h3><h1><b>Job Details:</b></h1><p></p><p></p><h2>Job Description: </h2><h1>Our Mission</h1><p><span>At 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. </span></p><p><span>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 users 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. </span></p><p><span>Were building intelligence that scales without sacrificing trust, cost, or the planet—because the future of AI should belong to the people it serves </span></p><p></p><h1>Role Summary</h1><p>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.</p><p>This is the rare skill that makes a hybrid, low-cost agent product viable.</p><p></p><h1>What you’ll do</h1><ul><li>Profile and optimize local inference (llama.cpp-vulkan and vLLM) for latency, throughput, and memory on edge hardware</li><li>Tune KV cache, continuous batching, and scheduling for interactive agent workloads</li><li>Drive quantization strategy (GGUF / AWQ / GPTQ) and validate quality impact with the Post-Training team</li><li>Cut CPU overhead and improve engine startup, model load, and lifecycle (start / stop / health)</li><li>Benchmark across hardware tiers and publish honest performance comparisons</li><li>Upstream fixes and patches to open-source engines where it helps us</li></ul><p></p><h1>What you’ll learn / grow into</h1><p><i>Curiosity is required. You will develop:</i></p><ul><li>The internals of modern inference engines and where the milliseconds actually go</li><li>Hardware-aware optimization across iGPU / CPU paths (Vulkan, SYCL, oneAPI, CUDA where relevant)</li><li>The quality-vs-speed-vs-memory trade space for small models</li><li>Interest in local / edge AI and squeezing hardware</li></ul><p></p><p>IMPORTANT:</p><p><i>Please be informed that Intel is proactively trying</i></p><p><i>to find candidates for this position which is frequently available</i></p><p><i>at Intel.</i></p><p><i>Please note that the position may not be available</i></p><p><i>at this time. If you would be interested in this position should it</i></p><p><i>become available, we would encourage you to apply, and our</i></p><p><i>hiring team will be glad to contact you when/if relevant. </i></p><p></p><p></p><h2><b>Qualifications:</b></h2><p>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.<br /><br />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.</p><h1></h1><h1>Required Qualifications</h1><ul><li>BS/MS in CS, EE, Math or related STEM field</li><li>5+ years software development background</li><li>Strong in C++ and/or Python; comfortable reading systems-level code</li><li>Understands how LLM inference works (attention, KV cache, decoding)</li><li>Has profiled and optimized real performance problems (CPU or GPU) and can prove the speedup</li><li>Linux, build systems, and low-level debugging expertise</li><li></li></ul><h1>Preferred Qualifications</h1><ul><li>Hands-on with llama.cpp, vLLM, ggml, or similar engines</li><li>Experience with GPU / accelerator programming (Vulkan, CUDA, SYCL, Metal) or SIMD / CPU kernels</li><li>Familiarity with quantization formats and their quality trade-offs</li><li>Open-source contributions to inference engines</li></ul><p></p><p>Requirements listed would be obtained through a combination of industry relevant job experience, internship experiences and or schoolwork/classes/research.</p><p></p><p><b>Benefits at Intel</b></p><p>Our total rewards package goes above and beyond just a paycheck. Whether youre looking to build your career, improve your health, or protect your wealth, we offer generous benefits to help you achieve your goals. Go to <a><b>Intel Benefits | Intel Careers</b></a> 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.</p><p></p><p> </p><p></p><p></p><h2>Job Type:</h2><p></p><p></p><h2>Shift:</h2>Shift 1 (United States of America)<p></p><p></p><h2>Primary Location: </h2>US, California, Santa Clara<p></p><p></p><h2>Additional Locations:</h2>US, Arizona, Phoenix, US, California, Folsom, US, Oregon, Hillsboro<p></p><p></p><p></p><p></p><h2>Posting Statement:</h2>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 status, marital status, pregnancy, gender, gender expression, gender identity, sexual orientation, or any other characteristic protected by local law, regulation, or ordinance.<h2></h2><h2>Position of Trust</h2>N/A<p></p><h2>Benefits</h2><p></p><p>We offer a total compensation package that ranks among the best in the industry. It consists of competitive pay, stock bonuses, and benefit programs which include health, retirement, and vacation. Find out more about the <a><span><u>benefits of working at Intel</u></span></a>. </p><p> </p><p> </p>Annual Salary Range for jobs which could be performed in the US: $170,500.00-315,490.00 USD<p> </p><p> </p>The range displayed on this job posting reflects the minimum and maximum target compensation for the position across all US locations. Within the range, individual pay is determined by work location and additional factors, including job-related skills, experience, and relevant education or training. Your recruiter can share more about the specific compensation range for your preferred location during the hiring process.<p> </p><p> </p><p></p><p><b>Work Model for this Role</b></p>This role will be eligible for our hybrid work model which allows employees to split their time between working on-site at their assigned Intel site and off-site. * Job posting details (such as work model, location or time type) are subject to change.<p></p><p>*</p><p></p>ADDITIONAL INFORMATION: Intel is committed to Responsible Business Alliance (RBA) compliance and ethical hiring practices. We do not charge any fees during our hiring process. Candidates should never be required to pay recruitment fees, medical examination fees, or any other charges as a condition of employment. If you are asked to pay any fees during our hiring process, please report this immediately to your recruiter.