k
kalaiy_gopal

Kalaiyarasi G

@kalaiy_gopal

AI Engineer , RAG Chatbots , PDF Data Extraction , WhatsApp Bots

Inde
Anglais, Tamoul
Certaines informations sont présentées en anglais.
À propos de moi
Hi, I'm Kalaiyarasi, an AI engineer who builds chatbots and automation that save businesses time. I help you: • Build a chatbot that answers questions from your own PDFs and documents (RAG) • Extract data from PDFs and scanned files into Excel or JSON using OCR + AI • Create a WhatsApp AI assistant for customer support Tools I use: Python, LangChain, FAISS, FastAPI, Streamlit, Gemini / GPT / Llama, Twilio and WhatsApp Cloud API. I explain things in simple words, deliver on time, and keep you updated at every step. Send me a message with your use case and I'll suggest the best approach.... Plus d’infos

Compétences

k
kalaiy_gopal
Kalaiyarasi G
hors ligne • 
Temps de réponse moyen de 1 heure

Voir mes services

Développement de chatbots d'IA
I will build a rag chatbot for your pdfs
Automatisations
I will extract data from pdfs and scans to excel or json

Portfolio

Expérience professionnelle

CogNet

AI and Automation Developer

CogNet • Temps plein

Jan 2026 - Present • 10 mos

Built an AI platform that extracts, validates and standardizes data from PDFs and scanned documents using OCR and LLMs, and generates reports from JSON and Excel data.

Least_Action

AI/ML Developer

Least Action • Temps plein

Aug 2025 - Dec 2025 • 4 mos

Built a WhatsApp chatbot using RAG, Meta WhatsApp Cloud API and Twilio, with document ingestion, vector search and multi-turn conversation memory. Built multi-agent AI workflows with LangGraph and PostgreSQL for goal tracking, sales follow-ups and content automation.

Gradtwin

Data Science Intern

Gradtwin

Feb 2025 - May 2025 • 3 mos

Built an AI document assistant for multi-format file querying (PDF, DOCX, CSV, etc.). Developed the system using LangChain for chunking, Sentence Transformers and FAISS for semantic search, and Groq API (Llama3) for grounded answers. Successfully reduced document query response times from minutes to seconds.