> 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

Start here. What I do, results, and where to go next.

## 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.*