Help & Supportcareers@gravityer.com
AI Engineer with 1+ years in Generative AI & Machine Learning
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Aspiring AI/ML and Generative AI Developer with hands-on experience in Python, FastAPI, LangChain, LangGraph, and TensorFlow. Skilled in ML, DL, NLP, RAG, and Agentic AI, with experience building AI-powered chatbots, REST APIs, and intelligent applications. Focused on delivering impactful AI solutions to solve real-world problems.
Kumararani Meena Muthiah College Of Arts And Science
Bachelor of Computer Application · Computer Application
August 1, 2022 – June 30, 2025
Chennai House Price Prediction
June 1, 2025 – June 1, 2026
Built a machine learning regression model to predict residential property sale prices in Chennai using structural, locational, and transactional features. Performed EDA, feature engineering, categorical encoding, and feature scaling. Trained multiple regression models (Linear Regression, Decision Tree, Random Forest, SVR, KNN). Random Forest delivered the best performance among all trained models, enabling accurate price predictions that support real estate valuation and investment decisions.
Agentic RAG Chatbot (Student Handbook & College Website)
June 1, 2025 – June 1, 2026
Built an Agentic RAG chatbot using LangGraph that intelligently routes questions between PDF documents and web search for context-aware, self-validated responses. Implemented an agentic graph pipeline using LangGraph with nodes for Planning, Retrieval, Web Search, Generation, Self-RAG validation, and Critique. Built a smart planner node that routes questions to PDF retrieval or live web search based on keywords and LLM decision. Generated embeddings using HuggingFace and stored in ChromaDB with Top-K similarity search. Delivered a chatbot that dynamically retrieves answers from PDF or live web based on user question type.
RAG - Powered Q&A Chatbot
June 1, 2025 – June 1, 2026
Built a Retrieval-Augmented Generation chatbot to answer user questions from uploaded PDF/DOCX using context-aware responses. Built FastAPI backend with /upload, /ask, /health REST endpoints handling multi-file ingestion and duplicate detection. Designed two-tier intent classifier: rule-based smalltalk detection + LLM fallback, reducing unnecessary API calls. Implemented RAG pipeline - HuggingFace embeddings, ChromaDB vector storage, Top-K retrieval, and Groq LLM generation. Delivered a full-stack AI application with a FastAPI backend and Streamlit frontend, supporting multi-format document ingestion (PDF/DOCX), intelligent intent routing, and context-grounded responses using RAG.
View ProjectCustomer Churn Prediction
June 1, 2025 – June 1, 2026
Built a machine learning model to predict whether a customer is likely to churn from a telecom service provider using demographic, service usage, and billing information. Performed EDA, feature engineering, categorical encoding, and feature scaling. Trained classification models (Logistic Regression, Decision Tree, Random Forest). The model helps telecom teams proactively target customers at high risk of leaving, improving retention and business.
Data Science Full Stack
Softlogic System (IBM Certified)
June 1, 2026 – Present
Cultural Fit Analysis
The candidate's projects are diverse within the AI/ML domain, covering Generative AI chatbots and traditional machine learning applications. This breadth suggests adaptability and a willingness to explore different problem spaces. The focus on practical, real-world applications aligns well with an engineering culture that values tangible outcomes. However, all projects are personal, and there's no team experience mentioned, which might impact cultural fit in a collaborative environment.
Soft Skills & Operational Fit
The candidate's project descriptions indicate a problem-solving mindset and an ability to translate business problems (e.g., customer churn, house price prediction) into AI/ML solutions. The detailed project tasks suggest an organized approach to development. However, without direct interaction or psychometric test results, it's difficult to assess communication, teamwork, or stress handling capabilities.