Git, Agile Scrum, Apache Spark, Python, Generative AI, AWS Bedrock, RAG architectures

AWS, Python, Azure, Gcp, MLops, Spark, Ray, Dask

triton , multi-threading, Tensorflow, memory pools, template programming, vLLM, TensorRT-LLM, XLA, CUDA programming, kernel scheduling, lock optimization, GDB debugging, operator fusion, memory access optimization, thread pools, graph optimization, GPU optimization, Warp execution models, RPC frameworks, performance profiling, TensorRT, VRAM scheduling