_ _ _ _ _
__| | __ _ _ __| |_| |__ | |__ | | __ _ _ __ ___
/ _` |/ _` | '__| __| '_ \| '_ \| |/ _` | '_ \ / __|
| (_| | (_| | | | |_| | | | |_) | | (_| | | | | (__
\__,_|\__,_|_| \__|_| |_|_.__/|_|\__,_|_| |_|\___|
I build backend systems and agentic AI pipelines — things that process data at scale, reason over documents, and get things done without hand-holding.
I move fast, own full cycles, and tend to automate whatever slows things down.
- Focus: Agentic AI, RAG pipelines, LLM orchestration, backend data systems
- Research background: NLP — Word2Vec, KMeans clustering, prompt engineering, LLM evaluation
- Currently building: AI agents — local open-source models, cloud APIs, whatever fits the problem
- Education: BS Computer Science, University of Dallas — Magna Cum Laude, Phi Beta Kappa
- Competitive programming: LeetCode · Kattis
Optimizing clustering of CDR3 sequences using natural language processing, Word2Vec, and KMeans Frontiers in Bioinformatics, Vol. 5, 2025
Applied Word2Vec embeddings, PCA, and KMeans clustering to T-cell receptor CDR3 sequences to identify immune activation patterns in ARDS patients vs. healthy controls. Presented at the 20th Annual Meeting of the MidSouth Computational Biology and Bioinformatics Society (MCBIOS).
Anansi — LangGraph pipeline that quizzes you on your own wiki using extended thinking
Agentic File Explorer — ReAct agent that navigates and reasons over a file system via natural language
AI Travel Agent — Hackathon runner-up: conversational flight search agent that parses intent from dialogue, queries Amadeus in real time via webhooks, and surfaces results with voice interaction
- Agentic systems that actually work reliably in production
- LLM pipelines for document understanding and extraction
- Backend architecture for data-intensive applications
- Picking the right model deployment for the right problem — local, cloud, or hybrid