Help & Supportcareers@gravityer.com
Data Science with less than a year in Machine Learning & Generative AI
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Data Scientist specializing in RAG applications, semantic search systems, and Agentic AI using LangChain — with production-ready deployments built on Streamlit. Developed a Hybrid RAG AI Assistant using LangChain, vector embeddings, and local LLMs for intelligent document Q&A; with context-aware retrieval, and deployed a churn prediction model achieving 86% accuracy (F1-score 0.86) with Random Forest. Proficient in Python, Scikit-learn, and Power BI, with a strong foundation in feature engineering, statistical model evaluation, and translating data insights into business decisions.
St. Dominic's College Kanjirapally, Kottayam
Bachelor of Science · Mathematics
January 1, 2022 – January 1, 2025
Luminar Technolab
Data Scientist (Intern)
June 1, 2025 – February 1, 2026
Cochin, Kerala, India
Hybrid RAG AI Assistant
June 1, 2026 – Present
Developed an AI assistant using Retrieval-Augmented Generation (RAG) to answer questions from uploaded PDF documents and live web sources Implemented semantic search via vector embeddings (sentence-transformers) and FAISS-based similarity search to retrieve the most relevant document chunks for context-aware retrieval Integrated a local LLM via Ollama for context-aware response generation and document summarization, enabling fully offline inference Built an Agentic AI pipeline using LangChain chain orchestration — supporting multi-step reasoning, tool use, and conversation memory Delivered an interactive Streamlit interface supporting document upload, Q&A; summarization, and persistent conversation history
View ProjectTelecom Customer Churn Prediction
June 1, 2026 – Present
Performed data cleaning and EDA to uncover churn patterns; applied SMOTE oversampling to address class imbalance Evaluated models using confusion matrix, precision, recall, F1-score, and ROC-AUC to select the best performer Achieved 86% accuracy and 0.86 F1-score with Random Forest; improved minority class (churn) recall from 84% to 87% Deployed the model as an interactive Streamlit web app for real-time churn prediction by business users
View ProjectRoad Accident Analysis Dashboard
June 1, 2026 – Present
Analyzed accident trends, casualties, and high-risk locations across multiple dimensions Designed interactive Power BI dashboards with slicers, filters, and KPIs for stakeholder reporting Used DAX measures to calculate accident severity indices and year-on-year trend comparisons
View ProjectMediCore – AI-Based Facial Recognition System
June 1, 2026 – Present
Built a deep learning-based facial recognition system for automated patient identification Reduced duplicate patient records through face verification and real-time identity matching Delivered a Streamlit interface for patient registration, photo capture, and live tracking
View ProjectPython Data Science with ML, AI & Power BI
National Council for Technology and Training (NCTT)
June 1, 2026 – Present
Python (Basics)
HackerRank
June 1, 2026 – Present
SQL and Relational Databases
IBM Developer Skills Network
June 1, 2026 – Present
Cultural Fit Analysis
The candidate's project portfolio shows a strong interest in applying data science to various domains, including AI assistants, business analytics, and healthcare. This diversity indicates an open-minded approach to problem-solving and a willingness to explore different challenges, which can be a positive cultural fit for dynamic environments. The focus on practical, deployable solutions (Streamlit apps) suggests a results-oriented mindset. The candidate is a fresher, so their cultural fit will largely depend on their ability to integrate into a team and learn from experienced members.
Soft Skills & Operational Fit
The candidate demonstrates initiative and a proactive learning attitude through self-directed projects and certifications. The ability to work on diverse projects (RAG, churn prediction, facial recognition, dashboarding) suggests adaptability and a broad interest in data science applications. Collaboration skills are mentioned in the internship description (Git/GitHub, model optimization). However, without direct interview data, a deeper assessment of communication, teamwork, and problem-solving under pressure is not possible.