
Data Science with less than a year in Machine Learning & LLM-based Applications
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Highly motivated and results-driven individual with 0.3 years of experience as a Technology Intern, specializing in Data Analysis, Machine Learning, and LLM-based Applications. Proficient in Python, FastAPI, Docker, and various ML/DL frameworks. Demonstrated expertise through impactful projects like a Cancer Gene Expression Classifier, an Intelligent Document Processing System, and an LLM-powered chatbot, showcasing strong problem-solving and technical skills.
Sahyadri College of Engineering and Management
B.E · Computer Science and Engineering (CSE)
August 1, 2021 – June 30, 2025
Logic Hive Solutions Pvt. Ltd
Technology Intern
February 1, 2025 – May 31, 2025
India
Cancer Gene Expression Classifier
June 1, 2025 – Present
Developed a machine learning pipeline to classify 5 cancer subtypes from 801 RNA-seq gene expression profiles, achieving 99.2% accuracy and 0.993 Macro F1-score using XGBoost with Optuna-based hyperparameter optimization. Applied ANOVA F-score feature selection to reduce 20,531 genes to the top 500 predictive biomarkers and leveraged SHAP explainability to identify key gene contributors influencing model predictions. Built and deployed an end-to-end workflow encompassing data preprocessing, model training, evaluation, and an interactive Streamlit dashboard, containerized using Docker for reproducible deployment.
DocuMind AI - Intelligent Document Processing System
June 1, 2025 – Present
Built an AI-powered document processing system to extract and summarize content from research papers and images using Tesseract OCR (PSM 6) and a local LLM (Qwen 2.5 via Ollama), ensuring high accuracy and data privacy. Designed a modular backend with FastAPI and an interactive UI using Streamlit, enabling seamless file uploads and real-time summarization. Containerized the application with Docker, optimizing performance by using a lightweight model to significantly reduce memory usage while maintaining accuracy.
Movie Recommendation System
June 1, 2025 – Present
Built a personalized movie recommendation system using User-Based and Item-Based Collaborative Filtering on the MovieLens dataset, achieving 0.90 RMSE and 0.70 MAE. Developed data preprocessing and model pipelines using Pandas, NumPy, and Scikit-learn, leveraging similarity metrics for accurate recommendations. Created an interactive Streamlit application for real-time movie search and personalized suggestions.
Deloitte Australia Data Analytics Job Simulation
Forage
June 1, 2025 – Present
Achieved an outstanding score of 94%, indicating a very strong grasp of data science and artificial intelligence principles and practical application.
Cultural Fit Analysis
The candidate's academic projects demonstrate a strong initiative and self-driven learning, tackling diverse problems from cancer subtype classification to LLM-powered document processing and recommendation systems. This breadth of interest and proactive project engagement aligns well with a culture that values continuous learning and innovation. The use of Docker for reproducibility also indicates an appreciation for best practices in collaborative development.
Soft Skills & Operational Fit
The candidate's project descriptions indicate a structured approach to problem-solving and a focus on delivering functional, reproducible solutions. The use of interactive dashboards and clear project goals suggests an ability to communicate technical results effectively. The internship experience, though brief, shows exposure to real-world application development and client interaction.
Strengths
Limitations