sinc-LLMThe engineer behind sinc-LLM
Mario Alexandre
I fell in love with AI before the AI boom.
AI Systems Engineer building production LLM infrastructure on an electrical engineering foundation.
I build the infrastructure that makes large language models work in production: continuously updating model substrates, multi-body adapter architectures with empirical retrieval gates, and the tooling that holds it together. I came to AI from electrical engineering, and I treat a model the way I was trained to treat a signal or a control loop, as a system you measure, bound, and prove, not one you hope about.
I founded sincllm.com and built the AI engineering practice and its technical stack. I build and run AI systems for client operations.
Why an electrical engineer builds AI systems
Find the signal hiding in the noise. That instinct does not care whether the system is a radio channel or a language model.
I came to this from electrical engineering. I hold a BS in Electrical and Electronics Engineering from the University of South Florida, my senior capstone designed a bidirectional DC/DC converter with MOSFET control and researched OFDM hybrid waveforms for 5G, and I keep a curated knowledge graph of the EE sources I still reason from. Then, in my last semester, I took a class on artificial intelligence, and that was the moment it clicked. I fell in love with AI before the AI boom. Everything I already loved, the sampling, the feedback loops, the discipline of proving a system before trusting it, was right there again, only now it was pointed at a machine that could reason.
Read the engineering background
What pulled me into engineering, and then into AI, is one feeling: walking into a field of pure noise and finding the signal buried in it. That is what logic actually is to me. Not a flash of genius, but the patient refinement of one step after another until the path to the goal resolves out of the static. Signal processing, control theory, and sampling taught me to do that with circuits and waveforms. A language model turned out to be the same problem at a larger scale: a vast, noisy space where the real work is shaping the input, bounding the behavior, and refining until the right answer separates from everything else. A prompt is a signal you can undersample. A model that drifts is a control system without a feedback loop.
The honest answer to the computer science versus electrical engineering question is that the work below needed both. The sampling theory that makes OFDM work is the same math under an adapter architecture, and the specification discipline that makes a system pass review is the same discipline taught in EE senior design, not in most ML bootcamps. The systems instinct never changed. Only the domain did.
What I have built
The projects below describe work from specification to deployment using Ousterhout interface-first discipline and Software Requirements Documents.
Technical SEO engineering.
Built a custom SEO engine with indexing, schema, and internal linking automation.
Article production pipeline.
Engineered transcript-blaster-v2 with Python 3.12, FastAPI, and a systemd deployment to a VPS for research, writing, and distribution.
Search discovery infrastructure.
Built AI engineering websites with schema, sitemap, and IndexNow engineering.
AI SMS outreach engine.
Built a production outreach system with AI-generated, per-recipient messaging on a $50 a month plan.
Browser automation.
Built a framework that drives live browser sessions through clicks and typing with session persistence.
Retrieval infrastructure.
Built a retrieval system with BM25 and dense fusion served on vLLM, plus a machine-readable llms.txt layer for a site’s knowledge.
Local knowledge infrastructure.
Built local-model RAG to extract company data, distill procedures, and train a self-hosted model, with a QA agent in the workflow.
Local and cloud model routing.
Built a multi-layer system that uses local models on company hardware and routes selected tasks to Claude, Codex, or a cloud model. Review data boundaries, output quality, and operating costs for the workload.
Infrastructure research.
Work includes continuously updating model substrates, multi-body adapter architectures with retrieval gates, and rank-one model editing, with specification and validation as part of the engineering process.
I run local inference on my own hardware, vLLM with Qwen 14B on an RTX 5090, and I operate the remote stack across a VPS, a Mac Mini, and Tailscale ingress. I would rather show you a system that works than a slide that says it could.
Education
The through-line across every project above is the same instinct an electrical engineer develops by necessity: measure the system, bound its behavior, prove it works before shipping it. That is what I bring to LLM infrastructure.
| Credential | Institution |
|---|---|
| BS, Electrical and Electronics Engineering | University of South Florida, Tampa, FL |
| Artificial Intelligence (coursework) | University of South Florida, Tampa, FL |
| AA, Engineering | Hillsborough Community College, Tampa, FL |
Building something that has to actually work?
Book a call, or reach out directly. I read every message.