https://github.com/anderson-ufrj/anderson-ufrj
Science Score: 26.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (7.8%) to scientific vocabulary
Last synced: 10 months ago
·
JSON representation
Repository
Basic Info
- Host: GitHub
- Owner: anderson-ufrj
- Default Branch: main
- Size: 13.7 KB
Statistics
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
- Releases: 0
Created 11 months ago
· Last pushed 11 months ago
Metadata Files
Readme
README.md
# Hi, I'm Anderson Henrique
**AI Systems Engineer | LLMs, RAG & MLOps**
*Building intelligent systems that solve real-world problems*
[](https://www.linkedin.com/in/anderson-h-silva95/)
[](https://github.com/anderson-ufrj)
[](https://huggingface.co/neural-thinker)
[](mailto:andersonhs27@gmail.com)
🎯 Professional Overview
3+ years building production Python systems with 2+ years specializing in AI/ML infrastructure. Computer Science background with proven expertise in multi-agent systems, API optimization, and scalable ML deployments.
📍 Location: Minas Gerais, Brazil • 🌍 Remote: Available worldwide • 🗣️ Languages: PT (Native), EN (Fluent), ES (Advanced), 中文 (Basic)
💼 Core Technical Expertise
| ### 🐍 **Backend Development** - **FastAPI** • **Django** async/await - **PostgreSQL** optimization & indexing - **Redis** caching strategies - **JWT** authentication & security - **Docker** multi-stage builds | ### 🧠 **AI/ML Integration** - **LangChain** orchestration pipelines - **RAG** systems & vector search - **ChromaDB** • **FAISS** semantic search - **HuggingFace** Transformers deployment - **Anomaly detection** (Isolation Forest, DBSCAN) | ### ☁️ **Infrastructure & MLOps** - **Kubernetes** container orchestration - **Prometheus/Grafana** monitoring - **GitHub Actions** CI/CD pipelines - **AWS** services & **HuggingFace Spaces** - **OpenTelemetry** distributed tracing |
🤖 Featured Project: Cidadão.AI
Multi-agent system for Brazilian government transparency analysis
🎓 **Computer Science Thesis Project** 🎓
*Currently being developed under supervision of*
**Ph.D. Aracele Garcia de Oliveira Fassbinder**
*IFSULDEMINAS - Instituto Federal do Sul de Minas Gerais*
### 🏗️ **System Architecture**
```python
# High-performance async agent orchestration
async def orchestrate_agents(task: AnalysisTask) -> Result:
async with asyncio.TaskGroup() as tg:
anomaly_task = tg.create_task(zumbi_agent.detect(task.data))
analysis_task = tg.create_task(anita_agent.analyze(task.contracts))
return await self.synthesize([anomaly_task.result(), analysis_task.result()])
```
🛠️ Technical Stack
FastAPI 0.109+ • LangChain 0.1+ • PostgreSQL 16 • Redis 7 • ChromaDB • Docker • Kubernetes
📈 Production Metrics
- 🤖 17 specialized agents processing government transparency data
- ⚡ <500ms p95 response time with FastAPI backend
- 🔍 Vector search across 1M+ document embeddings
- 🔒 JWT auth + rate limiting + comprehensive audit logging
- 📊 Real-time monitoring with Prometheus + Grafana stack
🌐 Live Ecosystem
[](https://neural-thinker-cidadao-ai-backend.hf.space/docs)
[](https://github.com/anderson-ufrj/cidadao.ai-backend)
[](https://anderson-ufrj.github.io/cidadao.ai-backend/docs/intro)
[](https://huggingface.co/spaces/neural-thinker/cidadao.ai-backend)
[](https://anderson-ufrj.github.io/cidadao.ai-docs/)
🧠 Engineering Philosophy
Bachelor's in Philosophy + Computer Science (in progress) shapes how I build systems:
Code as Applied Ethics: When handling public data, every design decision has moral weight. Privacy and transparency aren't features - they're foundations.
Dialectical Development: Thesis (requirement) → Antithesis (constraints) → Synthesis (elegant solution). Every sprint is a philosophical dialogue with the problem.
Epistemology in Practice: Code is crystallized knowledge. Good documentation isn't just helpful - it's how we share understanding across time and teams.
First Principles Thinking: Before optimizing, understand why something exists. The best performance improvement is often eliminating unnecessary complexity.
🚀 Project Ecosystem
🤖 Cidadão.AI Backend
Multi-agent system with 17 specialized AI agents, FastAPI async architecture, comprehensive monitoring
Impact: Processing 50k+ documents daily with 99.7% uptime
📱 Frontend Dashboard
Next.js 15 + TypeScript interface with real-time WebSocket connections, internationalization
Features: Real-time data sync, responsive design, dark/light themes
📚 Documentation Hub
Professional technical documentation with interactive agent showcase
Quality: ARIA accessibility, mobile-first design, bilingual support
🛠 Technical Environment
### **Languages & Core**
### **Frameworks & Libraries**
### **Data & AI/ML**
### **Infrastructure & DevOps**
🔥 Current Focus
Building cost-effective LLM inference pipelines and expanding multi-agent coordination capabilities.
🎯 Open to opportunities in: AI Infrastructure • Backend Systems • MLOps Engineering • Technical Leadership
📬 Let's Connect
**🟢 Status**: Available for new opportunities
**⏰ Response Time**: Usually within 24h
**🌍 Timezone**: UTC-3 (Brazil)
[](https://www.linkedin.com/in/anderson-h-silva95/)
[](https://github.com/anderson-ufrj)
[](https://huggingface.co/neural-thinker)
[](mailto:andersonhs27@gmail.com)
---
*"Building intelligent systems that bridge the gap between complex AI and practical solutions"*
🇧🇷 **Minas Gerais, Brazil** • 🌍 **Available for remote collaboration worldwide**
Owner
- Name: Anderson Henrique Da Silva
- Login: anderson-ufrj
- Kind: user
- Location: Brasil
- Company: Ruvixx, Inc
- Twitter: neural_thinker
- Repositories: 1
- Profile: https://github.com/anderson-ufrj
GitHub Events
Total
- Push event: 8
- Create event: 1
Last Year
- Push event: 8
- Create event: 1