AI Engineer with experience building RAG pipelines, LLM-integrated applications, and end-to-end ML s
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Final-year Integrated M.Tech (AI) student with experience building RAG pipelines, LLM-integrated applications, and end-to-end ML systems; skilled in Python, LangChain, prompt engineering, vector databases, and agent architectures.
Vellore Institute of Technology
Integrated M.Tech · Artificial Intelligence
August 1, 2022 – June 30, 2027
S. S. Heavy Equipments Pvt. Ltd.
Data Analytics Intern
November 1, 2025 – December 1, 2025
Pune, Maharashtra, India
RepoSage GitHub Repository Intelligence Assistant
May 1, 2026 – Present
Built an AI-powered repository assistant capable of querying 200+ code, commit, and issue chunks using natural language across GitHub repositories. Designed a multi-source RAG pipeline with AST-based Python chunking and regex parsing for 8+ programming languages, improving retrieval precision for code understanding tasks. Implemented semantic search with SentenceTransformers embeddings and ChromaDB across 3 indexed source collections, along with intent-based query routing and relevance filtering. Engineered an interactive Streamlit interface with relevance-threshold filtering and hallucination control via strict context grounding.
View ProjectExpenX - ML-Powered Expense Intelligence System
November 1, 2025 – November 1, 2025
Architected an NLP pipeline for automated expense categorization across 10+ spending categories from noisy transaction descriptions and structured data. Fine-tuned a SentenceTransformer-based model, improving macro F1-score by 12% over a TF-IDF + Logistic Regression baseline. Developed 3+ interactive dashboards to surface spending trends, recurring expenses, and anomaly patterns across transaction history.
View ProjectStress Monitoring System using Physiological Signals
April 1, 2025 – April 1, 2025
Developed an end-to-end predictive modeling pipeline for multi-class stress detection, achieving 92.8% accuracy on physiological sensor data. Applied feature selection and model evaluation across 2 classifiers (SVM, KNN), improving classification performance and inference stability. Implemented fuzzy logic rules to handle sensor uncertainty and improve decision boundaries in sensor-constrained environments.
View ProjectCultural Fit Analysis
The candidate's projects demonstrate a strong interest and initiative in AI/ML, which aligns well with an innovative and technically driven culture. The diversity of projects (code intelligence, expense categorization, stress monitoring) shows adaptability and a broad problem-solving mindset. The leadership roles in university clubs suggest an ability to contribute to team environments and take initiative. However, the limited professional experience makes it difficult to fully assess cultural fit in a corporate setting.
Soft Skills & Operational Fit
The candidate's project descriptions indicate an ability to work on complex problems independently and deliver functional solutions. Leadership roles in university clubs suggest teamwork and organizational skills. However, without specific behavioral assessment data, a comprehensive evaluation of soft skills and operational fit is limited.