Sreesha Braar

I’m a Generative AI Engineer focused on building Agentic AI (multi-agent workflows) and RAG systems that connect LLMs to real data and real tools.

Current focus areas

• Agentic AI / Multi-Agent Workflows: LangChain, LangFlow, LangGraph, CrewAI, AutoGen
• Retrieval-Augmented Generation (RAG): embeddings, chunking strategies, hybrid retrieval (BM25 + vector), vector databases, retrieval evaluation patterns
• GenAI APIs: Python + FastAPI, integrating LLM providers for chat/summarization/extraction use cases
• Automation & Workflows: n8n + Python + LLMs for operational automations (GTM / lead workflows)

Background

• 🎓 B.E. Computer Science — JSS Science and Technology University (2020–2024)
• 💼 Experience across GenAI engineering, full-stack development, and automation workflows

• LLM Applications: chat, summarization, extraction pipelines using LLM APIs
• RAG Systems: multi-document retrieval, hybrid search, vector stores, metadata filtering
• Agentic AI: tool-using agents, multi-step workflows, orchestration with LangGraph-style patterns
• Production APIs: FastAPI services for LLM + retrieval pipelines

Agentic AI • Multi-Agent Systems • LLM Applications • RAG Pipelines • Embeddings • Vector Databases • Hybrid Retrieval (BM25 + Vector Search) • LangChain • LangGraph • LlamaIndex • LangFlow • CrewAI • AutoGen • FastAPI • Python • Document AI • PDF RAG • Structured Outputs • Streaming APIs • Tool Calling

(Only included keywords that match your projects/experience written below.)

• Leading design and delivery of enterprise GenAI solutions for legacy workflows
• Integrating LLM-driven components into existing systems with focus on latency and reliability
• Collaborating with product/engineering teams to translate requirements into deployable GenAI architectures

Keywords: Generative AI LLM Applications RAG Python

• Built GenAI SaaS workflows and automation pipelines used in product operations
• Implemented GTM workflows using Clay, n8n, and LLMs
• Delivered systems from design to Dockerized deployment

Keywords: Generative AI LLM Automation n8n Clay Docker

• Developed autonomous agentic workflows using LangChain, LangFlow, LangGraph, and CrewAI
• Built RAG systems backed by vector databases for domain document retrieval
• Conducted applied experiments on AutoGen and Agent Zero patterns

Keywords: Agentic AI Multi-Agent Systems LangChain LangGraph RAG Vector Databases

• Built OCR-driven workflows and full-stack features using the MERN stack
• Developed REST APIs using FastAPI to support backend services

Keywords: FastAPI Python OCR MERN

• Engineered multi-PDF chat and summarization workflows using LangChain and LLM providers: Gemini, VertexAI, Groq
• Implemented hybrid retrieval using FAISS, AstraDB, MongoDB Atlas Vector Search, and BM25
• Developed a multi-threaded architecture for processing large documents
• Built multiple RAG variants using LangFlow, LangChain, and LlamaIndex with Google Drive integration

Keywords: RAG Hybrid Retrieval BM25 Embeddings FAISS AstraDB MongoDB Atlas Vector Search LangChain LlamaIndex LangGraph

• Built a web app using HTML, CSS, PHP, and MySQL with authentication and dashboards
  GitHub Repository

• Built a web application for connecting users and supporting collaboration features
  GitHub Repository

• Built an application exploring AI-assisted pet care features
  GitHub Repository

Thanks for visiting! If you're building LLM apps, AI agents, or RAG systems — happy to connect. 🚀