Miguel Fernández
Technical Lead at Browserbase
San Francisco, California, United States
Summary
🤩
Rockstar🎓
Top SchoolMiguel Fernández is a Technical Lead based in San Francisco with 8 years of experience building AI-powered products and accessibility-first web tooling. He combines hands-on ML engineering—contributing a browser agent using Llama 3.2 Vision for Meta’s popular llama-cookbook—with leadership roles at Browserbase and CRATUSTECH where he shipped production-facing systems. Miguel’s work uniquely bridges vision-language models, browser automation, and accessibility engineering, having built accessibility backbones and XPath tooling for AI web browsing frameworks. He has academic experience teaching and researching ML for dynamical control systems and a track record of turning research prototypes (smart microscopes, U-Net models) into deployable solutions. Equally comfortable writing quickstart notebooks for community adoption and guiding teams to production, he focuses on practical co-development of global AI.
8 years of coding experience
3 years of employment as a software developer
San José State University
Github Skills (17)
accessibility10
python10
llama10
llm10
ai10
playwright10
xpath10
typescript9
typescript-types9
jupyter-notebook9
typescripts9
selenium-ide8
selenium8
agent5
lm5
Programming languages (6)
Github contributions (5)
browserbase/stagehand
Jan 2025 - Mar 2025
An AI web browsing framework focused on simplicity and extensibility.
Role in this project:
Accessibility Specialist
Accessibility SpecialistContributions:37 reviews, 57 PRs, 123 pushes in 2 months
Contributions summary:Miguel primarily focused on enhancing the accessibility features within the `browserbase/stagehand` repository, an AI web browsing framework. Their contributions include developing an accessibility backbone, cleaning up and updating the accessibility tree, and generating XPath formats for elements within the accessibility tree. The user also made improvements to the accessibility tree structure, including cleaning and collapsing structural nodes. Their work is critical for ensuring the framework is usable by individuals with disabilities.
agentsaillmsplaywrightpuppeteer
meta-llama/llama-cookbook
Nov 2024 - Dec 2024
Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services
Role in this project:ML Engineer
ML EngineerContributions:1 PR, 1 comment in 11 days
Contributions summary:Miguel primarily contributed to the development of a browser agent using Llama 3.2 Vision, Playwright, and Together AI. Their work involved creating a quickstart Jupyter notebook for browser use, including setting up the environment, defining prompts for the LLM, and updating examples. The user implemented image encoding for vision queries and provided a demo link for the project.
aifinetuninglangchainllamallama2
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.