Skip to content
View thiagohsr's full-sized avatar

Block or report thiagohsr

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
thiagohsr/README.md

Hi, I'm Thiago Ramos πŸ‘‹

Software engineer with 15+ years across frontend, mobile, and full-stack development. Currently a React Native Engineer at BCA Europe, and spending my own time getting hands-on with agentic AI systems β€” LangGraph, multi-agent orchestration, and the infra that runs them.

  • πŸ“ Coimbra, Portugal
  • πŸ’Ό Currently: React Native Engineer @ BCA Europe (mobile frontend)
  • 🌱 Recently completed the Agentic AI Nanodegree (Udacity) β€” multi-agent systems, LangChain, CoT/ReAct
  • 🧭 Interested in Applied AI / Forward Deployed Engineer roles down the line, where sitting close to a real problem and owning it end-to-end matters, as well as full-stack roles building AI-driven product features
  • 🌐 Professional presentation: thiagoramos.interfacesdigitais.com.br
  • πŸ“« thiagoramos@gmail.com Β· LinkedIn

What I'm building

RoleSignal β€” a personal project, not a production product with real users. It's a demo dashboard running a 5-node LangGraph pipeline, streaming reasoning steps to the browser over a WebRTC data channel instead of polling. I use it to learn agent orchestration patterns and full-stack + infra ownership hands-on: a hybrid local/cloud LLM provider (Ollama with an OpenRouter fallback), a small AWS setup provisioned with Terraform, and a GitHub Actions deploy pipeline.

I write the specs, review every change, and make the architecture calls myself β€” an AI coding agent does a lot of the implementation. That workflow, knowing what to specify and what to check closely, is part of what I'm trying to get better at.

Tech Stack

Frontend & Mobile TypeScript React React Native Next.js

Backend & AI Node.js Python LangChain

Testing Jest Cypress

Also worked with AWS, Azure, and Docker across various roles; touched Kubernetes at Dasa Brazil and used Terraform while building RoleSignal β€” not areas I'd call myself a specialist in, but comfortable picking up when a project needs them.

A few things I've worked on

  • Part of the first team worldwide to deploy React.js to production (2015), on a checkout flow handling 2M+ daily accesses at Magazine Luiza
  • Cut list-loading latency from 7–13s to 500–800ms by migrating an Oracle-backed read path to Mongo (Dasa Brazil)
  • Delivered guest checkout for Christopher Kane's e-commerce platform, and shipped features for Harrods, Mackintosh, Neil Barrett, and JW Anderson (Farfetch tenants, via Present Technologies)
  • LangChain and prompt engineering on a healthcare voice-noting product (TeamEx / Clipboard Health); AI-integrated search at Tamanna.com

Pinned Loading

  1. cag-challenge cag-challenge Public

    CAG challenge - car list info

    TypeScript

  2. weather-app weather-app Public

    Weather app to attend code challenge for Tamanna

    TypeScript

  3. dasa-code-challenge dasa-code-challenge Public

    Dasa Code Challenge frontend

    JavaScript

  4. graphql-blog-api graphql-blog-api Public

    Forked from plinionaves/graphql-blog-api

    TypeScript

  5. spotippos spotippos Public

    rest api to spotippos

    Python

  6. teravoz-client teravoz-client Public

    Teravoz challenge

    JavaScript