Master's degree or higher in Computer Engineering, Computer Science, Applied Mathematics, or a related computing-focused degree, or equivalent experience
Required Previous Experiences
At least 3 years of relevant software development experience
Experience with PyTorch and HuggingFace
Experience with an LLM inference framework or deep learning compiler
Experience with performance modeling, profiling, debugging, and optimization of deep learning or high-performance applications
GPU programming experience with CUDA or OpenCL
Preferred Qualifications
Experience with TensorRT-LLM, SGLang, vLLM, lamma.cpp, or MLC-LLM
Understanding of LLM inference framework operations and end-to-end workflows
C/C++ software design, debugging, performance analysis, and test design