WELCOME TO THE WORLD OF
AI · ML · Engineer
I build AI systems that work outside a notebook autonomous agents, real-time computer vision, and production pipelines that solve real world problems.
I’m an AI/ML Engineer specializing in Generative AI, large language model systems, Agentic AI, Retrieval-Augmented Generation, and MLOps. I work at the intersection of AI engineering, software engineering, cloud infrastructure, and business impact—turning advanced AI capabilities into scalable, reliable, production-ready products.
At Uber, I contribute to real-time ML inference infrastructure supporting ride-demand forecasting with AWS SageMaker, Kubernetes, Python, and LangGraph. My work includes model-routing workflows that compare quality, latency, and inference cost across foundation and fine-tuned models, helping teams make smarter model-selection decisions.
Previously at KPMG, I built enterprise AI systems with measurable operational impact. These included a BERT and GPT-3 contract intelligence platform processing more than 40,000 clause types, a production RAG system using Azure OpenAI and Pinecone that reduced audit search time from 45 minutes to under 4 seconds, and Azure ML workflows that reduced model degradation incidents from 9 per quarter to 1. I also helped containerize 14 ML microservices with Docker and GitHub Actions, reducing deployment lead time from 8 days to 18 hours.
My personal projects extend this focus into LangGraph agents, LLM evaluation and observability, schema-grounded NL-to-SQL, OCR-based inventory automation, and demand forecasting. Across these systems, I focus on the engineering challenges that determine whether AI succeeds in production: evaluation, hallucination mitigation, observability, model routing, latency, cost optimization, responsible AI, and reliable deployment.
My long-term goal is to grow into a technical leader in Applied AI and Generative AI—helping teams transform emerging AI capabilities into dependable products while mentoring engineers and driving responsible innovation.
BVRITHCON-2023 International Conference · Published by Springer
My undergraduate thesis turned into a published paper. It compares Haar Cascade and MTCNN approaches for real-time face detection, evaluates LBPH recognition accuracy in a criminal identification context, and demonstrates the system working on live video. The research was accepted at an international conference and published by Springer.
doi.org/10.1007/978-981-95-0144-1_25Recent MS CS graduate at UNT. Available for AI/ML internships, research collaborations, and full-time roles. Let's create something extraordinary together.