AI Engineer
I build AI agents, data pipelines and the cloud plumbing that keeps them honest.
Multi-agent RAG with a 3-node LangGraph pipeline (retriever → answerer → critic) for independent verification. Dockerized FastAPI on AWS App Runner; ~850ms p50, 8/10 regression evals passing.
▸ run source ↗Multi-agent loan evaluation: document processing, deterministic risk scoring and generative-AI decision explanations.
▸ run source ↗Java 21 + Spring Boot 3 service benchmarked at 267K RPS across a 3-JVM cluster. Write-behind Redis cache (<1ms writes) with async PostgreSQL durability on virtual threads: 5× over synchronous writes.
▸ run source ↗SHAP-guided adversarial defense for vulnerability detection (ITNG 2025, Springer). Attack success rate 86% → 0% while holding 85%+ clean accuracy.
▸ run source ↗Go + AWS serverless impression pipeline: idempotent composite-key writes, a DLQ, and full Terraform IaC.
▸ run source ↗AI-augmented marketplace for near-expiry goods with TensorFlow.js quality checks and dynamic pricing. Pilot cut food waste 25% and lifted conversion 30%.
▸ run live ↗Academic portal for course navigation and graduation planning for 9,000+ students, with a Selenium scraper against Ellucian Banner.
▸ run live ↗Twitch-style VOD and clips platform with HLS streaming, clipping and full keyboard accessibility.
▸ run live ↗Fully serverless shoe marketplace on AWS: Lambda + API Gateway, DynamoDB, S3, Cognito, Stripe, CloudWatch and GitHub Actions CI/CD.
▸ private buildSHAP-guided test-time defense: BiLSTM + attention encoder, Platt-calibrated linear SVM and KernelSHAP attribution profiling to catch adversarial code edits without retraining the backbone.
1st place, Division 1 (LSU Baton Rouge), 5-hour algorithmic programming contest.
Tech talks, coding sessions and hackathons for 250+ students.
Honor society for academic excellence in computing.