Generative AI Engineer with less than a year in machine learning, NLP, and data science.
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Analytical, collaborative, and genuinely curious about data and AI – with strong communication skills and hands-on experience delivering end-to-end machine learning, NLP, and GenAI solutions.
Great Lakes
PGP · Data Science with GenAI & Artificial Intelligence
July 1, 2025 – January 1, 2026
Mewar University
M.Tech · Computer Science
N/A – Present
RTU University, ACEIT
B.Tech · Computer Science
N/A – Present
RAG-Based Document Q&A Chatbot
July 1, 2025 – January 1, 2026
Built a document ingestion pipeline using LangChain's RecursiveCharacterTextSplitter to chunk PDFs into overlapping segments; generated HuggingFace embeddings indexed into FAISS for sub-second cosine similarity retrieval. Engineered a LangChain retrieval chain pulling top-k FAISS chunks into a structured prompt – prompt engineered to restrict LLM responses to retrieved context, eliminating hallucination.
View ProjectPredictive Maintenance & RUL Estimation
July 1, 2025 – January 1, 2026
Engineered 35+ temporal features in Python using pandas and numpy – rolling means, lag variables, thermal stress ratios, vibration variance – on raw multivariate SCADA sensor data. Implemented machine-based train-test split via pandas groupby (by machine ID, not row index) to prevent data leakage; XGBoost regressor optimised via Optuna – final RMSE 17.88.
View ProjectHotel Booking Cancellation Prediction
July 1, 2025 – January 1, 2026
Built an end-to-end sklearn pipeline in Python using pandas for null imputation, encoding, and feature engineering across 119K+ records – lead-time buckets, deposit-type flags, market-segment encodings. Trained Logistic Regression, Random Forest, and XGBoost with stratified k-fold CV; tuned via GridSearchCV on precision-recall tradeoff – final model: accuracy 0.82, F1 0.87/0.72.
View ProjectSkill Match - Resume Intelligence System
July 1, 2025 – January 1, 2026
Built dual vectorisation branches in Python – sparse TF-IDF via sklearn TfidfVectorizer for keyword matching and dense Hugging Face embeddings for semantic similarity – computing cosine similarity scores to surface skill-fit percentage automatically. Integrated Google Gemini via LangChain as a second reasoning layer, passing similarity scores and skill deltas into a structured prompt to generate ranked gap analysis and matching insights.
View ProjectAutomated Job Intelligence & Outreach System
July 1, 2025 – January 1, 2026
Built a multi-threaded scraping engine in Python using Selenium and requests hitting 12+ job portals concurrently; applied sklearn TF-IDF + cosine similarity for NLP-based ghost-job detection and deduplication across a 14-day rolling window. Automated personalised cold-email outreach via smtplib with a Python idempotency log preventing duplicate sends; ranked output written to a colour-coded Excel dashboard using openpyxl with daily Top-20 picks.
View ProjectMathematical Modelling & Engineering Research - A Conceptual Framework for Skill Integration
IJEREAS
April 1, 2026 – Present
Rank 72 - Taxi Trip Distance Prediction Challenge
MachineHack
September 1, 2025 – Present
Cultural Fit Analysis
The candidate's academic projects demonstrate a strong interest and practical application in the Generative AI and Machine Learning domains, which aligns well with a Generative AI Engineer role. The diversity of projects, from RAG chatbots to predictive maintenance and resume intelligence, shows a broad skill set and adaptability. The ongoing PGP in Data Science with GenAI & AI further reinforces a commitment to the field. However, the lack of professional experience means cultural fit is primarily inferred from academic pursuits and project descriptions.
Soft Skills & Operational Fit
The candidate's project descriptions indicate an analytical and problem-solving mindset. The 'Automated Job Intelligence & Outreach System' project suggests an ability to build practical, automated solutions and manage data pipelines. The summary mentions 'analytical, collaborative, and genuinely curious,' which are positive indicators for operational fit, though these are self-reported and not directly validated by test results.