Responsibilities:

1.      Work on latest machine learning technologies

2.      Work on supporting for latest Linux operating system

3.      Work on AMD next generation GPUs/Accelerators

4.      Work on optimizing latest Rocm drivers and improve performance

5.      Design new machine learning technologies.

·        Deep Knowledge of C/C++ and Python programming

·        Experience with Linux Commands is must

·        Experience with Scripting language like bash/powershell 

·        Understanding of various python ML frameworks like Pytorch, Transformers etc

·        Understanding of various language and compiler for writing highly efficient custom Deep-Learning GPU Kernels. like Triton/Jax

·        Hands on Debugging Experience with gdb, valgrind etc

·        Experience and understanding of AI Models and Inferencing Engines like vllm/ollama/llama.cpp/sglang

·        Experience with Profiling tools needed to debug CUDA/ROCm Kernels like nsys/rocprof is a plus.

·        Knowledge of GPU architecture, PC architecture

·        Experience in writing ROCM/CUDA Kernels/Shader

·        Deep understanding and experience in implementation of Machine learning and AI algorithm.

·        Good communication skills and able to work with stakeholders effectively

·        Knowledge of x86 assembly language and x86/x64 CPU instructions is a plus