> For the complete documentation index, see [llms.txt](https://antoniovfranco.gitbook.io/antoniovfranco-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://antoniovfranco.gitbook.io/antoniovfranco-docs/overview.md).

# Overview

## Overview

Freelance AWS Machine Learning Engineer. I build cost-efficient ML systems.

São Paulo, Brazil (remote)\
<contact@antoniovfranco.com>\
[Website](https://antoniovfranco.com/) · [GitHub](https://github.com/AntonioVFranco) · [Medium](https://medium.com/@AntonioVFranco) · [LinkedIn](https://linkedin.com/in/antoniovfranco)

### What I do

* AWS ML architecture.
* Cost optimization for training and inference.
* PEFT fine-tuning: LoRA, QLoRA, QDoRA.
* Production MLOps: CI/CD, monitoring, retraining.

### Selected outcomes

* 40-60% AWS cost reduction on ML workloads.
* 5,000+ RPS inference with p95 under 100ms.
* Processing cost under 0.15 USD per document.
* 85% infra savings with multi-adapter serving.

### Deep dives

* [AWS ML architecture on AWS](/antoniovfranco-docs/deep-dives/aws-ml-architecture-on-aws.md)
* [AWS cost optimization for ML](/antoniovfranco-docs/deep-dives/aws-cost-optimization-for-ml.md)
* [Parameter-efficient fine-tuning (LoRA, QLoRA, QDoRA)](/antoniovfranco-docs/deep-dives/parameter-efficient-fine-tuning-lora-qlora-qdora.md)
* [MLOps and production ML systems](/antoniovfranco-docs/deep-dives/mlops-and-production-ml-systems.md)

### Portfolio

* [Services and engagement model](/antoniovfranco-docs/portfolio/services-and-engagement-model.md)
* [Client case studies](/antoniovfranco-docs/portfolio/client-case-studies.md)
* [Debugging and problem solving](/antoniovfranco-docs/portfolio/debugging-and-problem-solving.md)
* [Skills and tooling](/antoniovfranco-docs/portfolio/skills-and-tooling.md)
* [Writing and open source](/antoniovfranco-docs/portfolio/writing-and-open-source.md)

*Last updated: Jan 2026.*


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://antoniovfranco.gitbook.io/antoniovfranco-docs/overview.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.