pruning , Microservices, Pytorch, Docker, Python, AWS, Apis, Gcp, Azure, Kubernetes, data pipelines, speculative decoding, Distillation, evaluation frameworks, observability tooling, quantization, AI ML frameworks, TensorRT-LLM, LangChain, Triton Inference Server, vLLM, CI CD pipelines, LlamaIndex, cloud-native development, model optimization