Architect and implement LLM-based agent frameworks to support task automation and intelligent Develop and optimize RAG (Retrieval-Augmented Generation) systems using efficient chunking strategies for context-aware responses.
Use LangChain to orchestrate modular GenAI workflows integrated with vector databases (e.g., FAISS, Pinecone, Chroma).
Build and maintain knowledge graphs and incorporate Vision APIs for multimodal intelligence.
Apply advanced prompt engineering and token management to control costs and improve LLM accuracy.
Ensure reliability and robustness through hallucination control methodologies and responsible AI practices.
Design and deploy scalable GenAI applications on cloud platforms (Azure, AWS, or GCP).
Collaborate with cross-functional teams including data scientists, cloud engineers, and domain experts to integrate GenAI into products.
Leverage tools like Docker for containerization and Git for code versioning.
Use SQL and Python to process and manipulate data Skills :
Agent Frameworks (e.g., LangChain Agents)
Retrieval-Augmented Generation (RAG)
Chunking Strategies for document processing
Deep understanding of LLMs (e.g., OpenAI, Anthropic, Meta, Cohere)
Experience with AI services on Azure, AWS, or GCP (at least one)