$170,500 – $315,490
Listed on Intel’s own careers site. You apply with them directly — we never stand between you and the employer.
What this role is
Intel is seeking a performance engineer to optimize Large Language Model inference on their next-generation GPUs, working across the full stack from kernel development to open-source framework contributions. This role suits engineers passionate about squeezing maximum throughput from hardware and collaborating with the broader AI infrastructure community.
Our summary, not Intel’s wording. The full posting is on their site.
What they ask for
Required
- Bachelor's degree in Computer Science, Software Engineering, AI/ML or related field with 4+ years experience (or Master's with 3+ years, or PhD)
- 3+ years of software engineering experience in GPU computing, AI systems, or HPC
- Proficiency in modern C++ and Python
- Ability to read and modify complex systems-level code
Nice to have
- CPU/GPU architecture knowledge
- Understanding of LLM architectures and inference paradigms (attention, KV caching, continuous batching, speculative decoding, prefill-decode disaggregation)
- Prior open-source contributions to vLLM, SGLang, PyTorch, or llama.cpp
- Experience writing and optimizing custom GPU kernels with Triton, SYCL, CUDA/CUTLASS, or similar DSLs
- Experience with multi-node inference orchestration
- Daily use of AI coding agents to accelerate workflow