
AI Engineer with less than a year in Machine Learning & NLP
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Computer Science graduate with hands-on experience in Machine Learning, Deep Learning, NLP, LLMs, and Retrieval-Augmented Generation (RAG). Skilled in Python, PyTorch, LangChain, Hugging Face, FastAPI, and Docker, with experience developing and deploying AI-powered applications. Seeking a Data Science, Machine Learning, or AI Engineer role to build scalable, data-driven solutions and contribute to real-world business impact.
Kamarajar University, Madurai
B.Sc. · Computer Science & Mathematics
August 1, 2022 – June 30, 2025
Bdreamz
AI/ML Intern
December 1, 2025 – May 1, 2026
India
Dialogue Summarization System (NLP)
June 1, 2026 – Present
Developed an NLP-based dialogue summarization system by fine-tuning the Pegasus transformer model on a custom dataset using Hugging Face Transformers to automate accurate text summarization. Constructed a training pipeline incorporating data preprocessing, tokenization, transfer learning, and model evaluation using ROUGE metrics — achieving ROUGE-1: 45.30, ROUGE-2: 21.76, and ROUGE-L: 35.86. Exposed the model as a REST API via FastAPI, packaged with Docker, and hosted on Render to deliver automated summarization in production.
AI Insurance Chatbot
June 1, 2026 – Present
Designed and deployed a RAG-based conversational AI system leveraging LangChain and LLMs to accurately resolve insurance-related queries directly from policy documents. Engineered an end-to-end NLP pipeline encompassing document parsing, text chunking, embedding generation, and vector database (FAISS) for semantic retrieval, with fallback handling for out-of-scope queries. Built and exposed REST APIs using FastAPI, containerized the application with Docker, and deployed on Render to enable seamless real-time interaction.
Fraud Detection Using Graph Neural Networks
June 1, 2026 – Present
Architected a graph-based fraud detection system using Relational Graph Convolutional Networks (R-GCN) to uncover complex entity relationships within large-scale transactional data. Conducted exploratory data analysis (EDA) and transformed structured tabular data into graph representations by engineering node and edge features tailored for GNN-based learning. Benchmarked R-GCN against XGBoost as a baseline, tracked experiments via MLflow, and validated performance through real-world testing — confirming R-GCN superiority over traditional ML approaches in fraud detection.
Statistics
365 Data Science
June 1, 2026 – Present
Complete MLOps Bootcamp
Udemy
June 1, 2026 – Present
Data Science Course
Besant Technology
June 1, 2026 – Present
Cultural Fit Analysis
The candidate's project diversity (NLP summarization, RAG chatbot, GNN fraud detection) indicates a broad interest in AI applications. The self-initiated projects and certifications show a strong drive for continuous learning and self-improvement, which aligns well with a dynamic, innovation-focused culture. The target role of 'AI Engineer' is well-aligned with the candidate's demonstrated technical skills and project experience, suggesting a good cultural fit for a role focused on building and deploying AI solutions.
Soft Skills & Operational Fit
The candidate demonstrates a proactive attitude by undertaking personal projects that directly apply internship learnings and align with current industry trends in AI. The detailed project descriptions suggest good problem-solving skills and an ability to articulate technical challenges and solutions. However, without direct assessment data, specific soft skills like teamwork, leadership, or stress handling cannot be definitively evaluated.