Responsibilities :
Build and enhance AI agent workflows using frameworks such as LangGraph, LangChain, AutoGen, CrewAI, or equivalent technologies.
Implement AI agents for data discovery, profiling, enrichment, extraction, classification, contextual reasoning, and enterprise knowledge discovery.
Develop retrieval-augmented generation pipelines, including document chunking, embedding generation, metadata tagging, vector indexing, retrieval tuning, and response generation.
Work with vector databases such as Pinecone, Milvus, Qdrant, Weaviate, pgvector, Chroma, or equivalent technologies.
Build structured data agents that can connect to databases, inspect schemas, generate SQL, and support semantic understanding of enterprise data.
Implement document intelligence workflows for PDFs, Word documents, emails, transcripts, logs, and semi-structured enterprise content using Azure Document Intelligence, AWS Textract, LlamaParse, or equivalent tools.
Support prompt engineering, prompt testing, prompt versioning, and reusable prompt template development.
Implement AI evaluation routines covering answer quality, retrieval quality, hallucination checks, regression tests, robustness checks, and response consistency.
Support integration with LLM APIs and open-source models from providers such as OpenAI, Anthropic, Azure OpenAI, Hugging Face, Llama, Gemma, or equivalent ecosystems.
Technical and Professional Requirements:
Strong hands-on programming experience in Python and building AI agents.
Practical exposure to LLMs, RAG, vector databases, embedding models, prompt engineering, and AI application development.
Experience with one or more AI/LLM frameworks such as LangChain, LangGraph, LlamaIndex, AutoGen, CrewAI, Semantic Kernel, or equivalent tools.
Working knowledge of REST APIs, microservices, Git-based development, unit testing, and modern software engineering practices.
Familiarity with SQL and structured data concepts, including tables, schemas, joins, relationships, and query generation.
