AI Engineer: LLM agents, document AI, vision & speech.
I build software that does real work: LLM agents that act on codebases and dev workflows, vision and speech systems from dataset to deployed API, and the full-stack products around them. I care about what happens after the demo: tests, deploys, costs and the boring edge cases.
Tool-calling agents that read code, triage work, write fixes and open pull requests, with humans reviewing the result.
OCR plus LLMs with structured outputs, in production at 30,000+ documents a month and 97% accuracy. RAG over scanned PDFs.
Training CNNs from scratch and fine-tuning detection, segmentation and classification models. Datasets, benchmarks, APIs.
Real-time and batch Whisper transcription, on local GPUs and hosted inference, with voice activity detection and diarization.
LLMs and SLMs on llama.cpp for data that can't leave the machine, PII anonymization and GPU memory budgeting.
Rust services, Docker, CI/CD on Azure DevOps; Next.js, React, Supabase/Postgres with row-level security, offline-first PWAs.
B.S. in Information Systems · Minas Gerais State University (UEMG), 2025 · Portuguese (native), English (fluent)
100% local voice dictation for Linux and Windows. Press a hotkey, speak, and the text lands at your cursor. Silero VAD + whisper.cpp on CUDA. ~100 MB RAM and zero VRAM while idle.
Tray app that applies runes, summoner spells and item sets in the League of Legends client, over its local WebSocket API, with builds pulled through an MCP server. 1.5 MB binary, ~5 MB RAM, self-updating.
Natural-language questions to read-only SQL: the LLM classifies the question, inspects the schema and runs the query.
Containerized backend where an LLM agent performs CRUD through tool calls. Layered architecture, Docker Compose.
A guitar amp simulator in the browser: plug in, tweak the knobs, play. Web Audio waveshaping and convolution.
One Rust binary on an Android phone: axum + tokio, HTML compiled with maud, assets pre-compressed at boot, live telemetry over SSE.
Freelance work alongside my main job. Happy to walk through either one.
Multi-tenant scheduling for dental clinics: drag-and-drop weekly calendar, patient records with audit trail, per-role and per-dentist permissions, files on Cloudflare R2, tenant isolation with Postgres row-level security. Installable PWA.
Offline-first attendance for a factory floor: marks attendance with no connection, syncs through a queue, and enforces weekly rest-day rules.
A Samsung Galaxy A13 on my desk runs a single Rust binary (axum + tokio). The numbers below are read from /proc and /sys once a second and streamed to you over Server-Sent Events.
Type help. Or skip the browser entirely: curl -s fioravante.dev.br prints a card with live numbers from the phone.
Agents, document AI, vision, speech or the product around them. Happy to walk through any of it.