Skip to content
View negraodenio's full-sized avatar

Block or report negraodenio

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.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. 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
negraodenio/README.md

Hi, I'm Denio Negrão 👋

AI Systems Architect & Builder

Building production-grade AI systems for real-world and regulated environments.

I don't build demos. I build systems that operate.


🧠 What I Do

I design and build AI systems where reliability, security, governance and scalability matter.

With 20+ years of experience in technology, enterprise architecture, cloud and cybersecurity, I currently work on AI initiatives within a regulated financial-services environment, focusing on the secure adoption of Generative AI.

My focus areas include:

  • Production RAG systems
  • Multi-LLM orchestration
  • Agentic & multi-agent systems
  • AI architecture & enterprise integration
  • AI governance & Responsible AI
  • AI security & Secure AI by Design
  • AI evaluation & observability
  • LLM training, adaptation & local inference

🔥 LLM Work — Differentiator

LusoLLM

Portuguese-focused LLM optimized for local inference and enterprise environments.

👉 LusoLLM on Hugging Face

I don't just use LLMs — I adapt, engineer and deploy them.


🏗️ AI Systems Portfolio

🛡️ CodeGuard AI

AI governance system for code auditing, security and compliance.

Focus:

  • AI Security
  • AI Governance
  • GDPR
  • EU AI Act
  • Secure AI

🧠 AegisHub

AI system combining intelligent assistance, governance and compliance for regulated environments.

⚖️ CouncilIA

Multi-agent AI system for structured decision-making, evidence analysis and adversarial reasoning.

🎓 Polymath AI

AI learning system focused on personalized education, reasoning and autonomous coaching.

🌍 Nexus

AI-powered intelligence system for physical environments and Digital Twin scenarios.

⚙️ AI Development Runtime

Enterprise GenAI architecture for building production AI systems using:

  • RAG
  • Agents
  • Context Engineering
  • Tool Calling
  • Evaluation
  • CI/CD
  • Observability
  • Governance

🔐 AI Security & Governance

I work at the intersection of AI Engineering, Security and Governance.

Focus areas include:

  • Secure AI Architecture
  • AI Threat Modeling
  • Prompt Injection
  • Data Leakage
  • Agent Security
  • Tool & Function Calling Security
  • Guardrails
  • IAM & RBAC
  • API Security
  • AI Auditability
  • AI Risk Management
  • Responsible AI
  • EU AI Act
  • GDPR
  • OWASP Top 10 for LLM Applications
  • DevSecOps

I believe AI systems should be secure and governable by design, not secured after deployment.


💼 Enterprise & Financial Services Experience

Currently working on AI initiatives in a regulated financial-services environment, focusing on:

  • Generative AI adoption
  • Enterprise AI Architecture
  • LLM-based solutions
  • RAG and knowledge systems
  • Agentic AI
  • AI Governance
  • Secure AI by Design
  • AI risk and controls
  • Auditability and responsible AI

Previously worked in enterprise technology, cloud architecture and cybersecurity environments, including Capgemini Engineering and Devoteam, with strong experience in AWS, Cloud Security, enterprise integration and technical architecture.


🧩 Core Expertise

  • Generative AI
  • Retrieval-Augmented Generation (RAG)
  • Multi-LLM orchestration
  • LLM fine-tuning & local inference
  • Agentic AI
  • Multi-agent architectures
  • Context Engineering
  • AI Governance
  • AI Security
  • Enterprise AI Architecture
  • Cloud Architecture
  • AI Evaluation
  • Observability

🛠 Tech Stack

AI / LLM

OpenAI, Claude, Gemini, Qwen, DeepSeek, OpenRouter

Transformers, embeddings, fine-tuning, GGUF

Orchestration

LangChain, LangGraph, LlamaIndex

Backend

Python, TypeScript, Node.js, FastAPI

PostgreSQL, Supabase

Cloud & Infrastructure

AWS, Azure, Vercel

Docker, serverless architectures

Engineering

GitHub Actions, CI/CD, REST APIs


🚀 Current Focus

  • Enterprise AI Architecture
  • Production-grade RAG
  • Agentic & Multi-Agent Systems
  • AI Security
  • AI Governance
  • Secure AI by Design
  • LLM Engineering
  • AI Evaluation
  • Regulated AI Systems

⚔️ Positioning

I build AI systems that operate in production.

Not prototypes.

Not experiments.

Real systems.


📫 Connect


⭐ Selected Projects

  1. CodeGuard AI
    AI system for code auditing, security and compliance.

  2. AegisHub AI
    AI system combining intelligent assistance and governance.

  3. CouncilIA
    Multi-agent AI system for structured decision-making and adversarial reasoning.

  4. Polymath Engine
    AI learning system with personalized education and autonomous coaching.

  5. Nexus
    AI system for real-time intelligence in physical environments.

  6. AI Development Runtime / Skills
    Enterprise-grade GenAI stack for RAG, agents and CI/CD.


AI Architect | LLM Engineer | AI Security | AI Governance | Enterprise AI

Pinned Loading

  1. code-guard-ai code-guard-ai Public

    AI system for code auditing, security and compliance (GDPR, AI Act, etc..)

    TypeScript 1

  2. aegishub-ai aegishub-ai Public

    Mental health & compliance AI system aligned with Portuguese legislation

    TypeScript

  3. councilIA-system councilIA-system Public

    Multi-agent AI system for structured decision-making and adversarial reasoning

    TypeScript 1

  4. Polymath-Engine Polymath-Engine Public

    Self-evolving AI learning system with personalized education and autonomous coaching

    TypeScript

  5. nexus-system nexus-system Public

    AI system for real-time intelligence in physical environments

    TypeScript 1

  6. skills skills Public

    Enterprise-grade GenAI stack for building production AI systems (RAG, agents, CI/CD)

    1