ABOUT

Building Cloud, AI, and Scalable Systems

I'm a Master's student in Computer Engineering at UTD, focused on ML-powered and automated systems. I architect production-grade cloud infrastructure, build full-stack applications, and design interfaces that turn complex systems into something people can actually use.

CAPABILITIES

Full-stack. Cloud-native. Production-ready.

SELECTED WORK

Projects built for production.

FULL-STACK / AI

FieldTech Assistant

RAG-powered assistant for field technicians: manuals, wiring context, service history, QR asset lookup, offline-first PWA — FastAPI + React on Docker.

FastAPIReactChromaDBRAGPWA

Live Demo View Source

ML & TOOLING

ML Experiment Tracker MCP

MCP server for experiment runs, metrics, hyperparameters, and tags with SQLite persistence—plus a live dashboard to browse and compare runs.

PythonMCPSQLiteStarlette

Live Demo View Source

MCP & CLOUD

AWS CloudOps MCP

Read-focused MCP server for AWS ops (EC2, CloudWatch, ELB, Lambda, S3) via boto3—plus a live dashboard with synthetic inventory for demos.

PythonMCPAWSboto3

Live Demo View Source

MCP & OPS

Small Business Operations MCP

MCP server for tasks, expenses, CRM, and inventory with finance CSV analytics (margins, payroll, anomalies) plus a live ops dashboard on Render.

PythonMCPSQLiteStarlette

Live Demo View Source

CLOUD & FINANCE

Budget Insights Platform

Cloud-first finance platform: Flask transaction + analytics microservices, React dashboard, anomaly detection, and budget insights—live demo on Render.

ReactFlaskDockerAWS

Live Demo View Source

PRODUCT

Geofences Platform

Geofencing platform with Apple-inspired UI: create and monitor geofences, real-time notifications, track processing, and policy automation.

MapsReal-timeNotificationsAutomation

View Source

ML & DATA

pgvector RAG Demo

RAG chat app: PostgreSQL pgvector retrieval, sentence-transformers embeddings, and Streamlit UI with source citations.

PythonPostgreSQLpgvectorStreamlit

Live Demo View Source

© 2026 Oscar Valles