Diego Jose Robles Costa

CS undergraduate at the University of South Florida building production-grade AI software — LLM apps, inference gateways, and end-to-end web tools.

Tampa, FL · B.S. Computer Science, University of South Florida

Shipping AI software, end to end

I'm a computer science student at USF who ships production-grade AI software: a cross-platform LLM healthcare app presented at Google DevFest, a multi-provider AI API server with async streaming inference, and end-to-end web tools built without frameworks. I work hands-on with Python, C/C++, LLM application architecture, and API design — and I'm looking for a software engineering internship building AI and accelerated-computing products.

Where I've worked

IT Intern — WS Development

Jul 2026 – Present · Boston, MA

Administer 511 user identities across Windows Server, on-premises Active Directory, and Azure/Entra ID hybrid environments spanning 100+ retail and mixed-use properties and 400+ tenant companies. Remediated 193 NinjaOne-flagged vulnerabilities in six weeks while running recurring access reviews and resolving roughly 200 weekly tickets.

Cooperative Internship, Python & Database Development — Global Career Accelerator

Aug 2026 – Present · Tampa, FL

Selected for the Global Career Accelerator, a competitive internship program through USF focused on Python and database development, including a project with Intel analyzing data for real-world business cases. Collaborate with peers and industry experts in interactive, team-based sessions to solve technical problems and deliver structured project assignments.

Backend Developer Mentorship Program — Google Developer Group

Aug – Nov 2025 · Tampa, FL

Selected as 1 of 20 students for GDG Tampa's AI/ML and cybersecurity mentorship, building AI Doctor in Python under weekly mentor code review.

Highlight

Presenting AI Doctor App at Google DevFest

Last November at Google DevFest, we presented our AI Doctor App, the healthcare application my team and I built throughout the GDG mentorship program. Showcasing it to developers and industry professionals, and hearing their feedback on our architecture and user experience, it was an incredible experience.

The event offered more than the presentation itself. Hearing from experienced engineers and founders gave me new insight into model integration, responsible deployment, and how to position technical projects in a professional setting. I left motivated to keep improving the project.

What I'm working on

Offr+

GitHub ↗

A networking pipeline for finance students to connect with and organize their network.

Offr+ is an idea coming to life, something a few friends and I have been playing with for a few weeks. I've been the main developer while they generate ideas for features, tools, and produce the artwork. Contacts move through custom pipeline sections, follow-ups and coffee chats land on a calendar automatically, and applications and resume versions hang off the people who matter to them. Still in progress, and I'm looking forward to putting it in front of real users.

ReactTypeScriptSupabase

What's next

A chatbot that reviews and assesses resumes against the specific position being applied for.
Microsoft API integration to connect directly with Teams and Outlook.

Projects

01 ↗

Offr+ — Networking Pipeline for Finance Students

A pipeline for moving and organizing contacts from cold outreach through to real connections. About 9,800 lines across 11 pages, backed by 13 Postgres tables with 39 row-level security policies and three Supabase Edge Functions handling Microsoft Graph calendar sync, Teams meeting creation, and a cached job feed. I built my skills with React, Postgres, and OAuth mostly by breaking this software apart and working out the problems. Still a work in progress, and the project I'm most excited to keep building.

02 ↗

Ad+ — E-Commerce Advertising Platform

Local-first advertising dashboard shipped as a single self-contained HTML file — zero frameworks, zero backend. Four integrated modules: trending-product tracker, drag-and-drop kanban pipeline, automated outreach-letter generation, and a client-communication organizer.

03 ↗

AI Doctor — Cross-Platform AI Healthcare App

LLM-powered mobile app delivering symptom assessment, emergency detection, and provider suggestions — presented at Google DevFest. Dockerized FastAPI backend with layered LLM safety controls: guardrails and JSON-schema output validation.

04 ↗

AI-Server — Multi-Provider LLM API Server

Production-ready inference gateway unifying OpenAI, Anthropic, and Google LLM providers behind one REST interface — async request handling, token-streaming responses, Pydantic validation, per-client rate limiting, and structured logging.

05 ↗

Email Database

Lightweight in-memory database managing user records — built to strengthen low-level fundamentals in pointers, manual memory management, and data-structure design.

Credentials

Google AI Essentials

Google · Certificate of Completion

C++ Programming Fundamentals

Microsoft · via Coursera · Aug 2026

Verify credential ↗