I enjoy building AI and data-driven systems that solve practical problems through machine learning, NLP, analytics, and intelligent automation. My work focuses on combining strong technical foundations with real-world impact across healthcare, finance, and applied AI systems.

I am currently pursuing a Master's in Engineering Data Science at the University of Houston, where I work on projects involving predictive modeling, LLM applications, retrieval-augmented generation (RAG), analytics engineering, and explainable AI.

• Applied Machine Learning
• Generative AI and LLM Applications
• NLP and Retrieval-Augmented Generation (RAG)
• Predictive Analytics
• AI Agents and Intelligent Automation
• Data Engineering and Scalable ML Workflows

Built an end-to-end ML-driven investment research workflow using XGBoost, Random Forest, momentum-based ranking signals, portfolio backtesting, and RAG-powered financial insights.

Tech: Python XGBoost Random Forest FAISS RAG Pandas

Developed transformer-based abstractive summarization pipelines using BART and Mistral with LoRA fine-tuning, evaluated using ROUGE and BERTScore metrics.

Tech: PyTorch Transformers LoRA BART Mistral

Designed an LLM-driven agent workflow that filters job postings, ranks opportunities, and tailors resumes using tool-calling and structured reasoning.

Tech: Python Gemini API Groq API LLMs

Built an integrated multimodal AI pipeline combining text, audio, image, video, and document intelligence to generate structured incident analysis outputs.

Tech: YOLOv8 OCR NLP Streamlit Python

Created an AI-powered healthcare workflow assistant that converts vague operational ideas into structured, deployment-ready AI assistant specifications using prompt engineering and lightweight RAG grounding.

Tech: Python Streamlit OpenAI API RAG

Python SQL R

Scikit-learn XGBoost Transformers LLMs NLP RAG LangChain FAISS SHAP LIME

Pandas NumPy Power BI Tableau Matplotlib

Git Docker MongoDB MLflow ETL Pipelines

• Analyzed physician–AI interactions using lexical and semantic similarity methods
• Built automated Python and SQL preprocessing workflows for healthcare analytics
• Developed evaluation metrics and dashboards for AI-assisted communication systems

• Supported graduate students in NLP and explainable AI workflows
• Developed transformer-based and interpretability-focused learning notebooks
• Automated grading and feedback workflows using Python

• Built ML workflows involving preprocessing, feature engineering, and evaluation
• Applied explainability techniques including SHAP and LIME
• Improved predictive performance through model optimization workflows

MS in Engineering Data Science
2024 – 2026

Bachelor of Technology in Computer Science and Engineering
2020 – 2024

• LinkedIn: www.linkedin.com/in/sai-tanmai-burela
• GitHub: github.com/Tanmai019

I am actively interested in opportunities across:

• Data Science
• Applied AI
• Machine Learning Engineering
• Analytics Engineering
• AI Product Systems