1 day ago
Austin, TX, USA +3 moreMid Level
H1B sponsor
Base Salary
$171k - $315k/yr
Responsibilities
- Own the end-to-end optimization pipeline for running state-of-the-art LLMs on Intel GPUs.
- Profile, diagnose, and resolve cross-stack inference performance bottlenecks.
- Design, write, and optimize custom GPU kernels for attention mechanisms, MoE, quantization, and operator fusion.
- Upstream hardware backends and architectural improvements to vLLM, SGLang, PyTorch, and other open-source projects.
- Use roofline analysis and systematic profiling to inform GPU architecture and compiler roadmaps.
- Collaborate with hardware, architecture, compiler, and open-source communities on generative AI workloads.
Requirements
- Bachelor's degree in Computer Science, Software Engineering, Artificial Intelligence/Machine Learning, or a related field with 4+ years of experience; master's degree with 3+ years; or PhD.
- 3+ years of relevant software engineering experience in GPU computing, AI systems, or high-performance computing.
- Proficiency in modern C++ and Python, including the ability to modify complex systems-level code.
- Understanding of CPU/GPU architecture and modern LLM inference concepts including attention, KV caching, continuous batching, speculative decoding, and prefill-decode disaggregation.
- Preferred experience contributing to inference engines such as vLLM, SGLang, PyTorch, or llama.cpp.
- Hands-on experience with custom GPU kernels using Triton, SYCL, CUDA/CUTLASS, or other domain-specific languages.
- Experience with scale-out inference orchestration across multi-node topologies.
Benefits
- Competitive compensation package including stock bonuses, health benefits, retirement, and vacation programs.
- Hybrid work model allowing time both on-site at an assigned Intel site and off-site.
- United States locations include Santa Clara and additional sites in Folsom, Hillsboro, and Austin.
Categories
About Intel
Intel is a public semiconductor company that designs and manufactures CPUs and other silicon for PCs, servers, networking, edge, and embedded systems, and also offers foundry services plus AI and graphics accelerators. Founded in 1968 and headquartered in Santa Clara, it sells primarily to OEMs, cloud providers, and device makers worldwide. Its portfolio includes x86 processors (Core and Xeon), Ethernet and chipset products, and the Mobileye autonomous driving platform.