Rubens Zimbres
Embedded Files
Contact
Contact
Senior Data Scientist and Machine Learning Engineer, PhD
⚠ Disclaimer: five elements of this website were developed with Generative AI ⚠
Contributor for the cybersecurity project OWASP Top 10 for Large Language Model Applications and Agentic CTF
LATEST UPDATES
Build with AI Training - Gemini + AI Studio Workshop for Students and Developers at SENAI (National Industrial Service) - Brazil
In May, 2025 I was at Google I/O and the Google Developers Experts meeting in Mountain View and Sunnyvale.
I went to the AI Agent Conference in New York on May 6th, 2025, to talk about AI Agents' red teaming and privacy
👽 Google Developer Experts at Google Cloud NEXT '25 Las Vegas - Lounge 👽
Developer Keynote at Google Cloud NEXT '25 Las Vegas
👽 I was at Google Cloud NEXT '25 in Las Vegas , in a Lightining Talk. I lectured about multi-agent systems' security and privacy using Google Cloud technologies 👽
The CEO of Zendata and I presented our research at BlackHat Europe 2024, in London. We talked about multi-agents security and privacy.
Presentation of my 2024 work at AI/ML Community Summit in Budapest - Hungary
AI/ML Community Summit in Budapest - Hungary
Google facilities in Sunnyvale, California - North America Connect '24
👽 On April 9th I was on Google Cloud Next '24 in Las Vegas (Champions and Certified Lounge) presenting Langchain and Gemini deployed in a Google Cloud infrastructure (Dialogflow and Cloud Run) 👽
Google Cloud Champions Innovators at Next'24 Las Vegas
DevFest Experts Bootcamp in Sunnyvale - California
Google event in Colombia - NATION
APPS I DEVELOPED RECENTLY
APP 01 : IN-BROWSER LLM INFERENCE
IN-BROWSER LLM INFERENCE
I developed this app for sentiment analysis using tflite and Javascript. BERT model is transformed into a .tflite model. The JS code loads the BERT.tflite in the browser from a remote repo.
In-browser inference refers to the process of running machine learning models directly within a web browser, eliminating the need to send data back and forth to a server, as the App 01 does.
One can train any customized model in Tensorflow/PyTorch, convert to .tflite and deploy in the web browser.
APP 02 : REAL-TIME IN-BROWSER INFERENCE
The article explaining how to use a customized Tensorflow Lite model for in-browser inference is here.
IN-BROWSER ML INFERENCE
I developed this app for image classification using tflite and Javascript. Instead of the default and supported model EfficientNet, I used a PyTorch model. The JS code loads the quantized .tflite model in the browser from a remote repo.
This solution allows anyone to train any customized model in Tensorflow/PyTorch, convert to .tflite and deploy in the web browser.
APP 03: POSE DETECTION: LOCAL BROWSER INFERENCE
IN-BROWSER POSE ESTIMATION
This project creates a browser-based pose detection application using TensorFlow.js and its pose detection models (MoveNet, BlazePose, and PoseNet). The application allows users to activate their camera and see real-time skeletal tracking overlaid on their video feed, with options to switch between different pose estimation models.
By running directly in the browser using TensorFlow.js, this implementation offers significant advantages like client-side processing (reducing server load and latency), enhanced privacy (as video data remains local and isn't sent to external servers), cross-platform compatibility without installation requirements, and accessibility from any device with a modern web browser and camera.
The code handles camera access, video rendering, pose detection, and visualization of body keypoints with connecting lines to form a skeleton.
APP 04: ANDROID APP MADE WITH CODE ASSISTANT
Download and Install the App
Code of the project available at: https://github.com/RubensZimbres/Android-App
PROJECTS WE DELIVERED
IoT Projects
Projects We Delivered
Projects We Delivered
Some projects we delivered and their details: business needs, challenges and solution implemented.
Chatbots and Generative AI
Computer Vision Projects
ACTIVITY
My Google Developers profile
Articles about Google Cloud infrastructure, Vertex AI, Recommenders, Agent-Based Modeling, Graph Neural Networks, RAG. We have 17K views per month.
Articles about Google Cloud, Deep Learning, NLP, Agent-Based Modeling, Kubernetes, Transformers, Ethical Hacking, Pentesting, Social Networks
Python codes along my journey as Data Scientist. Machine Learning, Deep Learning, NLP, Transformers, Google Cloud, Algorithmic trading, Tensorflow, Keras and PyTorch
My profile at Google Experts Directory
My badges related to the courses and LABs I completed
My previous experience, education, licenses, certifications, published papers and patents
My questions and answers in StackOverflow. I am a recognized member of the Google Cloud Collective
My certifications in Machine Learning, Deep Learning, Google Cloud and Ethical Hacking
Academic papers published during my Master and Doctorate
My three patents, two in NLP and one in Cellular Automata
I am a featured contributor at Wolfram Community, with 2 Staff Picks and 40,000 article views
MY ARTICLES ON MEDIUM
In this article, you'll learn how to:
🔒 Use VaultGemma, Google’s first open-weight LLM trained from scratch with Differential Privacy (DP).
🛡️ Add another layer of privacy by fine-tuning it with Meta's Opacus library (DP-SGD).
💻 Run the entire workflow in VS Code connected to a free Google Colab T4 GPU—a brand new integration that’s a game-changer for productivity.
⚡ Make it all feasible on 16GB VRAM using 4-bit quantization and LoRA.
This article details a Financial AI Assistant built with Google's ADK, using a multi-agent system to answer user queries. It leverages a Neo4j graph database to store structured financial data and unstructured insights from SEC filings. Specialized agents then query this graph, perform RAG, or predict stock prices to provide comprehensive answers.
Here, I develop a multi-agent system that uses ADK (Agent Development Kit), Message Communication Protocol (MCP) server, a robust middleware enabling efficient agent communication, and the Agent-to-Agent (A2A) protocol, which allows AI agents to securely interact without exposing their internal workings.
Xtreme Weather App is an advanced disaster preparedness multi-agent system built with LangChain and Gemini-2.0-Flash that provides personalized emergency guidance using a Streamlit interface.
Build a Knowledge Graph with the help of Google’s Gemini and Neo4j, to better understand the disease, its causes, effects and possible treatments.
How to autoscale your website using Cloud Run.
A critique about a flaw in Kolmogorov-Arnold Networks, that seem to fit any random data.
Here, I used a customized Resnet50 in PyTorch to develop an in-browser inference with Tensorflow Lite and Javascript.
In this article I provide technical details of Gemini-1.5-Flash, benchmarks comparison and use cases exploring multimodality (text, audio, video and images)
Article about the use of neo4j-runway to turn CSVs into Knowledge Graphs and subsequent elaboration of a diagnostic hypothesis, using Gemini and no cypher.
Tutorial about fine tuning Google’s open model Gemma-2b via HuggingFace and PyTorch to solve Mathematical problems
Here, I host data and embeddings in a SQL instance and the Generative AI application will run on GKE. Similarity results will be given by a SQL query , inside the chatbot app.
Here, I explore the phases, methodologies, and potential impacts of a Transfer Learning attack.
Tutorial about building a Knowledge Graph from scratch using Neo4j and Cypher
Article about deploying Gemini on Google Kubernetes Engine (GKE) and Dialogflow.
In this article, I use LangChain and GPT-4 to evaluate Google’s open model Gemma-2B-it in 22 criteria.
I made Google's open source model Gemma collaborate with OpenAI’s gpt-3.5 to generate a graph plot from a simple natural language sentence at a low cost.
Here I create a Knowledge Graph storing scraped data in a structured manner, and using this data with LangChain to create a chatbot with memory
Article on how to use pgvector on a PostgreSQL database for RAG (Retrieval Augmented Generation) with LLMs.
A tutorial on how to identify the presence of Pegasus spyware on an iPhone
A Jupyter notebook about Two Towers Recommender in Tensorflow for Recruiting
Generative AI article on how to generate Python code using RAG + LangChain + LLM
Tutorial about installing an IDS for personal protection
OWASP Top 10 for LLMs, published at Google Developer Experts blog
Q&A Generative AI application in Google Cloud, published at Google Cloud blog
Generative AI automation to “read” and organize pedagogical projects in clusters
Setup of NVIDIA Merlin and Tensorflow for Recommendation Models, published in Google Developer Experts
Google Cloud Contact Center Artificial Intelligence (CCAI): A Managerial View
Two Towers Recommender: A Custom Pipeline in Vertex AI Using Kubeflow, published in Google Developer Experts
Search of Brazilian Laws using Dialogflow CX chatbot engine and Vertex AI Matching Engine
Graph Neural Networks: the message passing algorithm, published in Google Developer Experts
Develop Secure End-to-End Machine Learning Solutions in Google Cloud
My article on Attacking Active Directory in a Windows Server network with Kali Linux
Agent-Based Modeling with Python, NetLogo and Arduino
Burn a physical security key using a nRF52840 Dongle from Nordic to securely access your Google / Google Cloud accounts
In this article I will present the steps to create a Generative Adversarial Network.
In this post, I explain how to run an IoT project from the command line, using Ubuntu Core in a Raspberry Pi 3.
My first project with an IoT device and AWS IoT. It collects CPU Temperature in real time, send to Amazon AWS IoT and make it available for Machine Learning models and dashboards.
Based on people's contacts with each other, you can easily see the whole social network analysis.
My attempt to explain Schrodinger's Equation and CP Violation.
This is a code I developed with Wolfram Mathematica, while trying to solve an Atari game. An application in traffic is presented.
If you want to receive my articles on Medium, or provide feedback on this website. 💬
PRESENTATIONS
150_Machine_Learning_Formulas.pdfRECOMMENDED CONTENT
People of AI is a podcast of Gus Martins and Ashley Oldacre from Google showcasing inspiring people with interesting stories in the world of Artificial Intelligence (AI) and its subset, Machine Learning (ML).
The podcast will interview leaders, practitioners, researchers and learners in the field of AI/ML and invite them to share their stories, what they are building, lessons learned along the way, and excitement for the AI/ML industry.
For all the episodes, visit the People of AI page at: https://peopleofai.libsyn.com/
GALLERY
EXPERIMENTS
CONTACT
Page updated
Google Sites
Report abuse