Skip to content
View Alejandro-Candela's full-sized avatar
🏠
Working from home
🏠
Working from home
6 followers · 16 following

Achievements

Achievement: Pull SharkAchievement: QuickdrawAchievement: YOLO

Achievements

Achievement: Pull SharkAchievement: QuickdrawAchievement: YOLO

Block or report Alejandro-Candela

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
Alejandro-Candela/README.md

Alejandro Candela

AI Engineer | Agentic Systems Architect Specializing in Stateful Orchestration & Enterprise AI Automation.

Current Focus

I build production-ready AI systems that go beyond simple prompting. My architecture focuses on Stateful Agents and Hybrid Orchestration to solve complex, non-linear business processes.

  • Agentic Workflows: Advanced state management with LangGraph & PydanticAI.
  • Enterprise Automation: Bridging AI with existing stacks using n8n & custom integration layers.
  • Production-Grade RAG: Moving from naive RAG to Agentic Knowledge Retrieval (Graph-based & Hybrid Search).
  • Infrastructure: Microsoft Certified Azure AI Engineer (AI-102) with a focus on scalable, secure deployments.

Orchestration Patterns & Stack

  • Frameworks: LangGraph, LangChain, n8n, FastAPI.
  • Intelligence: Azure OpenAI, GPT-4o, Claude 3.5 Sonnet.
  • Vector / Knowledge: Neo4j (Graph), Pinecone, Azure AI Search.
  • Ops & Dev: Docker, Linux, CI/CD for LLM-based applications.

Featured Architectures

Hybrid Agentic Orchestrator (LangGraph + n8n)

A reference implementation of a stateful agentic system. It uses LangGraph for complex decision cycles and n8n for enterprise-grade "human-in-the-loop" and event-based triggers.

Agentic Knowledge Graph RAG

Solving the limitations of flat vector search by implementing a relational retrieval system using Neo4j and LangGraph-managed state.

Let's talk Architecture

I'm based in Madrid, Spain, working with partners in London (UK) and Germany (GmbH). I help companies transition from AI experiments to production-ready infrastructure.

LinkedIn • Inquiries

Pinned Loading

  1. agentic-solutions agentic-solutions Public

    CLI selector for enterprise AI agent stacks — 6 production-ready Golden Stack blueprints

  2. tennis-stats-analyzer tennis-stats-analyzer Public

    An end-to-end computer vision and machine learning system that processes tennis match videos to detect players and the tennis ball, compute shot speeds and player movement statistics, and generate …

    Jupyter Notebook 1 1

  3. Drowsiness-AI-detection Drowsiness-AI-detection Public

    Using OpenCV for gathering the images from webcam and feed them into a Deep Learning model which will classify whether the person’s eyes are ‘Open’ or ‘Closed’.

    Python

  4. agentic-rag-knowledge-graph agentic-rag-knowledge-graph Public

    Agentic knowledge retrieval redefined with an AI agent system that combines traditional RAG (vector search) with knowledge graph capabilities to analyze and provide insights about big tech companie…

    Python 4 4

  5. mercadona-agentic-assistant mercadona-agentic-assistant Public

    Python

  6. n8n_langgraph_POC n8n_langgraph_POC Public

    Hybrid Agentic Orchestration POC: Integrating LangGraph's stateful cyclic logic with n8n's enterprise automation and human-in-the-loop capabilities.

    Python