AI Engineer 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
Computer Science graduate with hands-on internship experience building Python pipelines, NLP workflows, and deep learning architectures. During my data science internship at AI Variant, I developed predictive models using large-scale datasets and gained hands-on experience in Machine Learning, Retrieval-Augmented Generation (RAG), Large Language Models (LLMs), vector embeddings, and Generative AI. I'm eager to apply these skills to build innovative, scalable, and data-driven solutions while contributing to the success of forward-thinking technology teams.
APJ Abdul Kalam Technological University
B.Tech · Computer Science
N/A – June 30, 2025
AI Variant
Data Scientist Intern
June 1, 2025 – March 1, 2026
Bengaluru, Karnataka, India
Hourly Energy Consumption Forecast
June 21, 2026 – Present
Architected a Deep Learning pipeline using LSTM, GRU, and RNN architectures to forecast hourly energy demand, outperforming baseline statistical models to achieve a robust, cross-validated R² of 0.93 and a MAPE of 0.04. Conducted advanced Time Series Decomposition and statistical testing to identify trends; engineered features for 10+ annual U.S. holidays to improve model sensitivity to demand spikes. Implemented rolling-window validation with a 48-hour look-back and hyperparameter tuning via GridSearchCV, resulting in an optimized 30-day forecast.
GenAI-Powered Drug Review Analysis and Patient Query Assistant
June 21, 2026 – Present
Built a Generative AI chatbot that analyzes drug reviews and answers patient queries using a Retrieval-Augmented Generation (RAG) pipeline. Implemented vector search with FAISS and embedding models to retrieve contextually relevant review information for accurate response generation. Orchestrated LLM workflows using LangChain and Hugging Face models, enabling context-aware question answering and efficient information retrieval.
Alzheimer's Disease Classification
June 21, 2026 – Present
Developed a machine learning pipeline comparing 12 classification models, including CatBoost, XGBoost, and SVM, achieving 83.7% accuracy and strong ROC-AUC performance. Engineered a robust preprocessing workflow incorporating IQR-based outlier capping, feature scaling, and class imbalance handling through advanced sampling techniques. Performed model benchmarking using Confusion Matrices and ROC analysis, emphasizing high recall to reduce diagnostic false negatives.
Cultural Fit Analysis
The candidate's projects show a diverse interest in AI applications, from energy forecasting to drug review analysis and disease classification, which aligns with an innovative and problem-solving culture. The internship experience indicates an ability to integrate into a professional team environment. However, the candidate is still early in their career, and the breadth of experience is primarily academic and personal projects, which might require some ramp-up in a fast-paced industry setting.
Soft Skills & Operational Fit
The candidate demonstrates an ability to work in a team (collaborated with a 4-person team) and translate technical insights into business reports. The focus on rigorous evaluation frameworks and modular pipelines suggests an organized and quality-conscious approach to work. However, without specific psychometric or English test scores, a deeper assessment of stress handling, logical reasoning, and communication clarity in a professional setting is limited.