Full Stack AI Engineer | Specialized in AI-powered solutions for regulated industries

Building production-grade AI systems that process 4,000+ documents with <2s latency. Currently managing critical banking infrastructure (1M+ records) while developing scalable LLM applications for healthcare, government, and enterprise clients.

• AI Integration: Implementing GPT-4, Claude API, and RAG architectures in production environments
• Full-Stack Development: Building scalable apps with Django/FastAPI backends and React/Next.js frontends
• Data Infrastructure: Managing SQL Server/Oracle databases and designing ML-optimized ETL pipelines on AWS
• Automation: Reducing operational time by 40-90% through intelligent process automation

• 🏦 Full Stack Developer @ Superintendency of Banks (Dominican Republic) - Managing production databases with 1M+ records
• 💻 ML Specialist / AI Engineer @ Upwork - Building AI-powered solutions for global clients
• 🔧 Full-Stack Engineer @ RBTrends - Developing AI applications for healthcare and government

AI & Machine Learning

TensorFlow • PyTorch • Scikit-Learn • OpenAI API • Claude API
LangChain • ChromaDB • RAG Architecture • NVIDIA Riva

Backend & APIs

Python • Django • FastAPI • Flask • REST APIs • GraphQL

Frontend

React • Next.js • JavaScript • Alpine.js • HTMX • Tailwind CSS

Cloud & DevOps

AWS (EC2, Lambda, S3, SageMaker, ECS, Glue) • Docker • Kubernetes
GitHub Actions • CI/CD • Render

Databases & Data Engineering

SQL Server • Oracle • PostgreSQL • MongoDB
PySpark • Airflow • ETL Pipelines • BigQuery

• ⚡ 99.9% uptime on production AI systems processing 4K+ records
• 🚀 70-90% reduction in manual operation time vs traditional processes
• 📈 40% latency reduction in RAG implementations
• 🎯 55% conversion rate increase through ML-powered customer segmentation
• 🔧 24+ production tickets resolved in critical banking systems

Flask-based system integrating OpenAI, Claude, and Gemini APIs for automated Jira/Confluence documentation generation

• Impact: 60% reduction in manual task time
• Stack: Flask, OpenAI API, Claude API, Gemini API

AWS-based transcription system with GPT-4 integration for automated content analysis

• Stack: NVIDIA Riva, AWS (ECR, EC2, Lambda, API Gateway), GPT-4
• Features: Real-time processing, automated responses

Vector embedding-based document processing with semantic search

• Performance: <2s latency on 4,000+ documents
• Stack: Django, ChromaDB, RAG architecture, ETL pipelines

Full-stack application for healthcare providers with GPT-4 integration

• Uptime: 99.9% in production
• Stack: Django, FastAPI, React, Claude API

Looking for: Collaborations on AI/ML projects, open-source contributions, and freelance opportunities

Open to interesting projects and collaborations in AI/ML space