AI Frameworks Engineer
Core
Develop and optimize AI inference frameworks (vLLM, PyTorch) and GPU compute kernels for large language models on Intel GPUs.
Role type
Senior IC AI Frameworks Engineer (LLM inference)
Builds
Open-source LLM inference frameworks and optimized GPU kernels
Domain
AI/ML Infrastructure, GPU Computing, Data Center
Deliverable
production ML models
Required skills
Python, PyTorch internals, LLM inference, Linux, distributed computing, performance profiling
Preferred skills
GPU kernel development (Triton, CUDA, SYCL), vLLM, quantization (FP8/INT8/INT4), open-source contributions
Technologies
vLLM, PyTorch, Triton, SYCL, CUDA, OpenCL, Linux
Responsibilities
Design and optimize AI framework software for LLM inference; Develop and tune compute kernels for transformer operations; Implement distributed execution paths; Profile workloads to identify and resolve performance bottlenecks; Optimize code for specific hardware backends; Build and extend unit tests and performance regression coverage.
Seniority
Senior, hands-on IC
