Generative AI and Large Language Models (LLMs), Microsoft Azure, FastAPI, Python, Azure OpenAI AI services, RAG embeddings vector semantic search and prompt engineering, Authentication and API security concepts, REST API design and integration, Docker and containerised application deployment, Git and version control, SQL and relational databases, Application debugging logging and troubleshooting

large language models (LLMs), multi-agent workflows, embedding-powered retrieval solutions, GenAI-based systems

large language models (LLMs), Python, Sklearn, FastAPI, LangChain, CrewAI, Hugging Face Transformers, generative AI solutions, Plotly, Vapi, TRL, Salesforce AgentForce, Google Agent SDK, OpenAI Agent SDK, Microsoft Copilot, Dialogflow

Performance Monitoring, Python, prompt frameworks, LLMs, RAG vector databases, data ML libraries, data platforms, MLOps pipelines, Agentic AI systems, multi-agent workflows, enterprise APIs, retrieval strategies, operational systems, tool orchestration, evaluation pipelines, observability feedback loops

Retrieval-Augmented Generation (RAG), Large Language Models (LLMs), Apis, Google Cloud, Git, Typescript, Docker, Azure, Python, Kubernetes, AWS, LangChain, CrewAI, AI orchestration frameworks, Prompt engineering, Vector databases, Memory architectures, LangGraph, AutoGen, CI/CD pipelines, Embedding models, Multi-agent systems

.NET, Model Context Protocol (MCP), Retrieval Augmented Generation (RAG), Large Language Models (LLMs), Machine Learning, Amazon S3, ELT, Python, AWS, Java, Artificial Intelligence, Sql, Spark, Databricks, Rest Apis, Etl, Apache Iceberg, Airflow, Pinecone, Vector Search, Chroma, semantic search, Generative AI, Agentic AI, dbt, Delta Lake, Milvus