Docker, AWS, Apis, Gcp, Cloud Infrastructure, Python Programming, Azure, Kubernetes, GPU pooling, AI Agentic, Benchmarking, TensorRT, GPU acceleration, caching strategies, Dify, LLM SGLang, quantization, Compute, RAG architectures, CrewAI, LangChain, CLI tools, vLLM, agent frameworks, AutoGen, Ollama, LlamaIndex, LLM serving engines