Mexico City, Mexico

Enrique Ríos Flores

AI Engineer · Infrastructure & LLM Systems

AI Engineer with a quantitative background in Physics and Mathematics (IPN). Specialized in the end-to-end lifecycle of Generative AI systems: from orchestrating complex multi-agent architectures using the Model Context Protocol and n8n automation, to deploying open-weight models and managing on-premise bare-metal infrastructure and Kubernetes clusters.

  • Multi-Agent Orchestration
  • Model Context Protocol
  • Agentic RAG
  • LLM Serving & Optimization
  • On-Premise & Kubernetes
  • Computer Vision Pipelines
01

Experience

AI Engineer · MOBO

Dec 2025 — Present
  • Autonomous Agent Systems: Designed and deployed autonomous multi-agent systems (CrewAI, LangGraph, Hermes, Phi), implementing the Model Context Protocol, structured tooling and function calling, and state machines with n8n.
  • Agentic RAG & Knowledge Integration: Integrated Agentic RAG workflows, strategic context management (context window optimization and harnessing), and multi-source connectivity using vector embeddings, graph databases (Neo4j), and DAX cubes.
  • LLM Serving & Optimization: Deployed and served open-weight models (Llama, DeepSeek, Qwen) using vLLM to maximize throughput, minimize latency, and optimize operational costs.
  • Infrastructure & Gateway Management: Administered on-premise bare-metal servers and Kubernetes clusters for AI workloads, managing routing, rate limiting, and security via Kong API Gateway.
  • Computer Vision Pipelines: Architected multimodal computer vision pipelines (Gemini API + YOLO) for real-time video analytics and operational incident detection.

AI & Systems Infrastructure Engineer · PEMEX

Jan 2025 — Aug 2025
Internship
  • End-to-End System Deployment: Led the complete deployment of the MAAe platform (Advanced Model for Evidence Analysis), covering database design, backend, frontend, and core processing engines.
  • Infrastructure Virtualization: Orchestrated and virtualized infrastructure using Docker and Docker Swarm, ensuring high availability, portability, and fault tolerance across local servers.

Systems Architect & Technical Project Lead · Indava

Nov 2022 — Dec 2025
  • Core Architecture & Legacy Migration: Led software architecture and legacy system migrations to Laravel, integrating custom automation workflows with enterprise ERPs (Odoo) across key projects: TAP Terminal, PLMA, IncFile, IRE-TCMC.
  • LLM & Data Processing Integration: Implemented AI pipelines with OpenRouter for enterprise LLM adoption, large-scale web scraping (Selenium, BeautifulSoup), and AI-driven unstructured data processing.
  • Process Modeling & Knowledge Bases: Designed complex business logic using 4-level DMNs and BPMN modeling, and automated technical wikis connected to internal knowledge bases.
02

Stack

Orchestration & Agents

  • CrewAI
  • LangGraph
  • Hermes
  • Phi
  • Model Context Protocol
  • Tooling Skills
  • Context Management & Harness
  • n8n (State Machines)
  • OpenClaw
  • NemoClaw

Models & RAG

  • Llama
  • DeepSeek
  • Qwen
  • Agentic RAG
  • Embeddings
  • Neo4j
  • YOLO
  • Multimodal LLMs

DevTools & AI-Native Engineering

  • Claude Code
  • OpenCode
  • OpenRouter
  • vLLM
  • Function Calling (Pydantic / Instructor)
  • Structured Outputs

Infrastructure & Servers

  • On-Premise / Bare-Metal
  • Kubernetes
  • Docker
  • Docker Swarm
  • Kong API Gateway
  • Linux / Bash
  • CI/CD

Development & Data

  • Python (Advanced)
  • FastAPI
  • Flask
  • SQL
  • DAX Cubes
  • REST APIs
  • Git / GitHub
  • C
  • Odoo ERP
03

Background

Education

  • B.S. in Physics and Mathematics

    Instituto Politécnico Nacional (ESFM)

    2018 — 2023

Languages

  • SpanishNative
  • EnglishB2 Proficient