Applied AI Frameworks Engineer
Core
Designing and developing features for Intel's AI frameworks software stack, specifically inference serving and ML frameworks for AI accelerators and GPUs.
Role type
Senior IC Applied AI Frameworks Engineer
Builds
Inference serving frameworks (SGLang, vLLM) and ML frameworks (PyTorch, Tensorflow, JAX) for Intel AI accelerators and next-gen GPUs.
Domain
Hardware-accelerated AI inference and training
Deliverable
production ML models
Required skills
Advanced C++ (14/17), Python, parallel programming, ML kernel development (GEMM, Convolution, Flash attention), Deep Learning/LLM knowledge, complex system debugging, computer architecture, HW-SW optimization
Preferred skills
CUTLASS or Triton kernel development, compiler algorithms for heterogeneous systems, Fuser optimizations
Technologies
SGLang, vLLM, PyTorch, Tensorflow, JAX, C++, Python, CUTLASS, Triton
Responsibilities
Design and develop SW features for AI frameworks (HW-agnostic and HW-aware), enhance Deep learning training and Inference capabilities, identify optimization opportunities for DL workloads, participate in Open-source community development
Seniority
Senior, hands-on IC
