AWS, Pytorch, Python, Kubernetes, Azure, Docker, Gcp, model monitoring, AI ML frameworks, LlamaIndex, evaluation harnesses, hallucination mitigation, LangChain, cloud-native development, CI CD pipelines

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