Sree Kumar

Sree Kumar

AI Engineer & Python Developer

Bengaluru, IndiaArtificial Intelligence and Software Development
1roles
63skills
1education

About

AI Engineer with two years of experience designing, building, and deploying production-grade Generative AI systems, including LLM-powered chatbots, agentic AI workflows, RAG pipelines, and conversational voice agents.

Experience

AI Engineer & Python Developer

Thor Signia

7th July 2024 – 10th July 2026 · Bengaluru, India

Designed and deployed production GenAI applications including LLM-powered chatbots and RAG pipelines, improving customer service automation by 75%. Architected LangChain and MCP-based retrieval, prompt-engineering, agentic tool-use, and function-calling workflows. Built full-stack AI web and mobile applications with Python, FastAPI, Django, React.js, and React Native. Deployed containerized AI services with Docker on AWS; implemented Azure AI Search and Azure OpenAI RAG systems. Built secure REST APIs with JWT authentication, optimized MySQL and SQL/NoSQL data pipelines, and reduced load times by 40% through profiling, caching, and inference optimization. Delivered 5+ end-to-end AI and web projects with 100% client satisfaction and on-time delivery.

Education

Dr. K.V. Subba Reddy Institute of Technology, Kurnool

Bachelor of Technology, Computer Science & Engineering

2020 – 2024

CGPA: 7.65

Skills

Generative AILarge Language Models (LLMs)LLM Integration & OrchestrationAgentic AITool UseRetrieval-Augmented Generation (RAG)LangChainMCP ServersModel Context ProtocolFunction CallingPrompt EngineeringContext Window ManagementNLPVector DatabasesSemantic SearchEmbeddingsConversational AIChatbot DevelopmentConversational Voice AgentsElevenLabsOpenAI APIsAnthropic Claude APIsAzure OpenAIAzure AI SearchAzure OpenAI EmbeddingsPythonFastAPIDjangoDjango REST FrameworkRESTful APIsJWT AuthenticationMulti-process ArchitectureEvent-Driven ProgrammingMySQLSQLNoSQLSQLAlchemyVector StoresDockerAWSReact.jsReact NativeExpo RouterJavaScriptGitGitHubVS CodeAgile DevelopmentPython (Programming Language)ChatbotsProduct Life CycleWeb CachingScalable ArchitectureNLP LibrariesCloud ApplicationsAmazon Web Services (AWS)Skilled Multi-taskerOptimisingREST APIsAWS CloudFormationAI AgentsTeam LeadershipAgentic AI Development

Projects

Enterprise RAG Assistant — Azure AI

Built an enterprise RAG pipeline using Azure AI Search for vector and hybrid retrieval and Azure OpenAI for embedding generation and grounded answer generation. Implemented department-level access control, query rewriting, reranking, evidence-sufficiency checks, conflict and date awareness, citation validation, FastAPI endpoints, structured logging, and Application Insights integration. Across 14 evaluation cases, improved groundedness from 0.929 to 1.000, citation correctness from 0.786 to 0.857, and reduced hallucination rate from 0.071 to 0.000.

AI Chatbot System with RAG

Architected a customer-service chatbot combining semantic search, retrieval, embeddings, and NLP with a FastAPI/Django backend. Built containerized web and mobile deployments with event-driven architecture for concurrent AI conversations.

AI Voice Agent — ElevenLabs Workspace

Built a conversational AI voice agent using ElevenLabs conversational AI models and integrated Twilio telephony to place and receive calls and conduct programmatic end-to-end conversations.

Business Card Scanner — Mobile Application

Built a React Native application using OCR and AI-powered extraction to automate data entry. Implemented a RAG-backed knowledge base for contextual research on scanned content with a Python backend.

Profit Simplified — Affiliate Marketing Platform

Developed referral tracking in Python and Django to attribute users acquired through affiliate links, and built coupon creation and management tied to referral tracking for commission attribution.