AI/ML Engineer · Generative AI · MLOps · NLP · RAG . AWS · Azure · GCP ·
Building intelligent systems that solve real-world problems at scale
I'm an AI/ML Engineer with 3+ years of experience designing and deploying production-grade machine learning systems across finance and healthcare domains.
Currently at Fifth Third Bank, I build end-to-end AI pipelines for fraud detection, RAG-based document intelligence, and real-time expense analytics — working with LangChain, GPT-4, FAISS, and pgvector over financial documents. Previously at Capgemini, I built clinical ML systems for patient readmission prediction and NLP-powered EHR processing.
- 🔭 Building Generative AI & RAG pipelines for large-scale financial document processing
- 🧠 Published researcher — ACM CHI 2025 on mobile app privacy transparency
- 🎓 M.S. Computer Science @ Kent State University (2024–2025)
- 💡 Passionate about responsible AI, MLOps at scale, and healthcare ML
- 🚀 Exploring on the AI side: LangGraph, multi-agent LLM systems & prompt engineering
- 🔬 Exploring on the ML side: PEFT/LoRA fine-tuning, model optimization & distributed training
| Degree | Institution | Duration |
|---|---|---|
| 🎓 M.S. Computer Science | Kent State University, Kent, OH, USA | Jan 2024 – Dec 2025 |
| 🎓 B.E. Electronics & Communication Engineering | MITS University, Andhra Pradesh, India | June 2018 – May 2022 |
| Project | Description | Tech |
|---|---|---|
| 🔍 Visual-Reality-Showdown-AI-vs.-Reality | Classifying AI-generated vs. real images using deep learning | Python, PyTorch, CNN, ResNet50, InceptionV3, Jupyter Notebook |
| 📊 customer-behavior-prediction | Predicting potential buyers through purchase trends & event analysis | Python, Scikit-Learn, Pandas, Matplotlib, Jupyter Notebook |
| Flight delay forecasting using ML & data visualization | Python, Scikit-Learn, Pandas, Seaborn, Jupyter Notebook | |
| 🧬 Cancer Gene Expression Clustering | RNA-Seq PANCAN tumor gene expression clustering | Python, Scikit-Learn, K-Means, PCA, Jupyter Notebook |
| Fine tune with Mistral with QLORA&PEFT | Efficient fine-tuning of large language models — Mistral-7B and LLaMA — using QLoRA | Lora,Peft,Pytorch,Huggingface,LLM Fine - Tuing |
Donku, B. (2025). Discrepancies in Mobile App Permissions: Exploring Transparency and User Awareness in the Android Ecosystem.
ACM CHI Conference on Human Factors in Computing Systems. [Primary Author]
"Building AI that's not just powerful, but trustworthy."