AI Engineer with less than a year in RAG systems and Python.
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
M.Tech Computer Science graduate (Parul University, 2026) specializing in LLM engineering and RAG system development using LangChain, FAISS, and Groq API. Published author at PICET 2026 and ICONDEEP 2026 on ML and Explainable AI. Completed 6-month industry training in Machine Learning & AI at Maruti Infosoft. Targeting fresher-level AI/ML or LLM Engineer roles where I can build and ship production AI systems.
Parul University
M.Tech · Computer Science
August 1, 2024 – June 30, 2026
Parul University
B.Tech · Computer Science
August 1, 2020 – June 30, 2024
Maruti Infosoft
Machine Learning Intern
December 1, 2025 – June 1, 2026
India
Slash Mark
Python Developer Intern
January 1, 2024 – April 1, 2024
India
RAG-Based Document Question Answering AI System
June 1, 2026 – Present
Built a production-ready RAG pipeline using LangChain and Groq LLM (Llama-3.3-70B), enabling natural language querying over uploaded PDF documents with context-aware answer retrieval. Implemented document chunking, HuggingFace vector embeddings, and FAISS-based semantic search; optimized chunk size and retrieval parameters for high-relevance responses. Deployed full-stack application via Streamlit web interface, supporting real-time document Q&A with sub-3-second retrieval; codebase structured across ingestion, retrieval, and generation modules — available on GitHub.
Heart Disease Prediction using Machine Learning (Research)
June 1, 2026 – Present
Built a predictive ML model to classify heart disease risk using multiple classification algorithms. Applied SMOTE to handle class imbalance and performed EDA using Seaborn and Matplotlib. Compared Logistic Regression, Random Forest, and SVM to select the best-performing model.
Movie Recommendation System using Machine Learning
June 1, 2026 – Present
Built a hybrid recommendation engine combining content-based filtering (TF-IDF on genres, cast, keywords) and collaborative filtering (user-item matrix) for personalized movie suggestions. Processed and cleaned large movie datasets, engineering features for similarity computation. Implemented cosine similarity to match user preferences with relevant movie titles effectively.
Data Sprint 2026
Machine Learning Hackathon
June 1, 2026 – Present
Bridging Accuracy and Interpretability: A Hybrid XAI Framework for Heart Disease Prediction
ICONDEEP
January 1, 2026 – Present
An Analytical Review of Heart Disease Prediction Models Based on Machine Learning
PICET
January 1, 2026 – Present
Cultural Fit Analysis
The candidate's academic projects cover diverse areas like RAG systems, heart disease prediction, and movie recommendation, showcasing a broad interest in AI applications. The internships, though short, indicate exposure to industry practices. The target role of 'AI Engineer' aligns well with the candidate's specialization in LLM engineering and RAG system development. The breadth of skills and project diversity suggest adaptability and a willingness to explore different problem domains within AI.
Soft Skills & Operational Fit
The candidate's resume highlights 'Problem Decomposition', 'Independent Research', and 'Technical Communication' as soft skills. These are valuable for an AI Engineer role, especially in tackling complex problems and collaborating within a team. The academic projects and internship experiences suggest an ability to work on structured tasks and contribute to project workflows.