RAG (Retrieval-Augmented Generation), Large Language Models (LLMs), Flask, FastAPI, Rest Apis, Python, LangChain, Generative AI, AI Agents, LangGraph, Prompt Engineering, LlamaIndex

Container orchestration (Docker, Kubernetes), Cloud platforms (AWS, Azure), Machine Learning, Jax, Deep Learning, Tensorflow, MLops, Pytorch, Gcp, Python, Computer Vision, Generative AI, AI workflow orchestration frameworks, Transformer-based architectures

triton , Docker, Rest Apis, Kubernetes, Python, Tensorflow, Pytorch, Gcp, FastAPI, Azure, AWS, data pipelines, Hugging Face, vLLM, prompt engineering, multi-agent workflows, Agentic AI, FAISS, retrieval, ChromaDB, RAG pipelines, embedding generation, model serving

Docker, Flask, FastAPI, Python, Pinecone, LangChain, LLMs, LLaMA, Hugging Face Transformers, SLMs, embedding models, GPT-3.5, Claude, Mistral, FAISS, RAG, Weaviate, LanGraph