RAMYA RANGARAJU
DALLAS, TX • +1-940-****-***• *****************@*****.***
Data Science Engineer skilled in Python, SQL, Tableau, and cloud tools (AWS, GCP), with hands-on experience in machine learning, multimodal analytics, and data-driven product development. Proven track record in optimizing pipelines, automating reports, and building AI/ML models that improve decision-making and operational efficiency. Seeking opportunities to develop scalable data products and drive business impact through statistical rigor and engineering excellence. EDUCATION
UNIVERSITY OF NORTH TEXAS, DENTON, TX Aug 2023 – May 2025 Master of Science in Data Science
Relevant Coursework: Data Modeling, Software Engineering, Machine Learning, Cybersecurity, Data Analytics, Large-Scale Data Visualization.
SKILLS
Languages: Python, R, SQL, Shell Scripting, Bash
Data Analysis & Visualization: Pandas, NumPy, Matplotlib, Seaborn, Tableau, Power BI, Excel, Plotly Machine Learning & NLP: Scikit-learn, BERT, CLIP, Wav2Vec2, TCAV, TensorFlow, PyTorch, Keras, XGBoost, LightGBM, NLTK, spaCy, Transformers (HuggingFace)
Cloud & Big Data: AWS (S3, Lambda, SageMaker), GCP (BigQuery, Vertex AI), Azure ML, Apache Spark, Hadoop, Databricks
Databases: MySQL, PostgreSQL, MongoDB, SQLite
Tools: Jupyter Notebook, Git, GitHub, VS Code, Postman, Pytest, Docker, MLflow, DVC, Airflow Workflow & Agile: Jira, Trello, Agile (Scrum), SDLC PROFESSIONAL EXPERIENCE
COGNIZANT Nov 2021 - Jun 2023
Data Analyst
• Analyzed autonomous vehicle data using Python, SQL, and Tableau to detect anomalies and optimize fleet operations
• Automated reporting workflows with Apache Airflow, reducing manual effort by 40%.
• Developed interactive dashboards to track KPIs (safety, ride disruptions), improving stakeholder visibility.
• Supported A/B testing and geospatial analysis, leading to a 15% increase in trip efficiency.
• Ensured data quality and collaborated in cross-functional Agile teams for faster product iteration.
• Built predictive models using scikit-learn to identify vehicle fault likelihood, improving preventative maintenance scheduling by 18%.
• Implemented data validation scripts to flag telemetry anomalies in near real-time, reducing data processing lag by 25%.
• Led a cross-functional data QA task force that resolved 100+ schema issues, enhancing the accuracy of fleet analytics and executive reporting.
PROJECTS
Multimodal AI for Toxicity Detection Feb 2025 – Apr 2025
• Built AI models (BERT, CLIP, Wav2Vec2) to detect and rewrite toxic content across text, image, and speech.
• Evaluated outputs with BERTScore, BLEU, and TCAV; implemented fairness checks and visual dashboards. StrikerStats – Sports Analytics Platform Sep 2024 – Dec 2024
• Designed a scalable MySQL-based system to track real-time soccer stats (players, matches, performance).
• Integrated role-based access, advanced SQL queries, and dashboard visualizations for end-users CERTIFICATIONS
• IBM Machine Learning Professional Certificate
• Generative AI Essentials and Prompt Engineering for ChatGPT (Coursera)