Data Scientist & AI Engineer — Columbus, OH
6+ years turning complex data into decisions. From large-scale risk models at Amazon to LLM-powered research tools at Ohio State — I build things end to end, care about reliability, and communicate clearly across technical and non-technical teams.
Background, impact, and what I'm working toward
My path into AI started with a background in Electronics Engineering and grew through five years at Amazon, where I built production ML systems for fraud detection and risk analytics at global scale. I completed my Master's in Information Technology at the University of Cincinnati in 2024, and I'm currently a Senior Research Data Analyst at Ohio State University — building ML pipelines and AI-powered tools for academic research.
Right now I'm deepening my expertise in generative AI, LLM fine-tuning, and agentic architectures through a dedicated AI engineering program — and actively building enterprise-grade AI projects in healthcare intelligence, fraud detection, and ML observability.
I hold a DP-203 Microsoft Certified: Azure Data Engineer Associate certification and have two IEEE publications in applied ML and NLP.
What I work with day to day
Python, PyTorch, TensorFlow, Scikit-learn, XGBoost, classification, regression, anomaly detection, time-series forecasting (SARIMA, Prophet)
LangChain, LangGraph, OpenAI API, RAG pipelines, embeddings, vector databases, fine-tuning (LoRA/PEFT), agentic workflows, LLM evaluation
MLflow, Docker, GitHub Actions (CI/CD), AWS SageMaker, Azure, model versioning, drift detection, automated retraining, observability
SQL (advanced), PostgreSQL, MySQL, Pandas, NumPy, ETL pipelines, Kafka, feature engineering, large-scale data processing
Text classification, NER, topic modeling, sentiment analysis, summarization, Hugging Face transformers, document understanding
Power BI, Tableau, Matplotlib, Seaborn — executive dashboards, KPI reporting, data storytelling for non-technical audiences
Enterprise AI systems built from scratch
An enterprise-grade RAG application that ingests 100+ healthcare policy documents, compliance guidelines, and research papers. Stakeholders query across the full document corpus in natural language and receive cited, accurate answers with source attribution. Includes auto-generated summary reports and data visualizations — deployed on AWS with hallucination detection and guardrails.
A multi-agent system built with LangGraph: Agent 1 ingests and validates transaction data, Agent 2 runs XGBoost anomaly detection and risk scoring, Agent 3 auto-generates executive risk reports with visualizations — fully automated end-to-end. Full audit trail logging, retries, and fallbacks. Real-time Streamlit dashboard showing risk scores and business KPIs.
A production ML observability platform monitoring model performance, data quality, and feature drift in real time. Automatically triggers retraining when drift thresholds are breached and notifies stakeholders. Dashboard shows live accuracy, precision/recall trends, feature importance evolution, and business KPI impact — updated on a configurable schedule.
Where I've worked and what I've built
Peer-reviewed IEEE research
Open to data science and AI engineering opportunities
I'm actively looking for roles in data science, ML engineering, and applied AI — particularly in healthcare, FinTech, or AI/SaaS environments. If you're working on something interesting, I'd love to hear from you.