VázquezDev
/

YOUR NEXT HIRE ISN'T HUMAN.

AI Systems Architect & Developer_

Most companies are bleeding money on operations AI should already own.

I design and develop Autonomous Agent Systems and Enterprise RAG Architectures that eliminate manual workflows.

VAZQUEZDEV.PRO
ONLINE
Adrian Vazquez Vazquez - AI Systems Architect & Developer.

#About Me_

You

Who is Adrian Vazquez and what does he do?

Vb
Cortex AI

Adrian isn't a conventional developer.

He turns manual operations into autonomous AI workflows. Production-grade systems that integrate into your business, run 24/7, and don't need a team behind them to work.

His mission: return time and capital to the companies bold enough to deploy AI before their competitors do.

Ask me anything about Adrian's work, stack or approach... on Cortex AI
Powered by VazquezDev AI Solutions.

>> // SYSTEMS DEPLOYED _

Real architectures. Real results. Available to build for you.

SOL-01
VazquezDev
RAG · AI System
In Development
01

Cortex AI

VazquezDev's portfolio needed to do more than be read — it needed to answer. Cortex AI turns static pages into a live conversation.

01SITUATIONThe Problem

The Problem:

A traditional portfolio is a passive document. Recruiters and potential clients spend seconds scanning it — and leave without grasping the depth of the work. VazquezDev needed a way to turn passive visitors into active conversations: answering specific questions on demand without forcing anyone to read page by page.

  • Static pages can't answer “what's your RAG stack?” or “have you done this before?”
  • VazquezDev's work spans too many dimensions to fit in a simple scroll
  • Most portfolio visitors leave with an incomplete picture
02OBJECTIVEThe Objective

Objective:

Turn vazquezdev.pro into an interactive layer where anyone can query the full professional profile — experience, projects, stack, and services — in a single natural-language flow:

  • One entry point for everything: experience, projects, stack, services
  • Multilingual from day one
  • Fast, low-latency answers — no waiting
03SOLUTIONThe Tech

Stack & highlights:

  • Frontend: Vue 3 · Vite
  • Backend: FastAPI · Python
  • Vectors: ChromaDB — lightweight self-hosted storage
  • LLM: Groq API — ultra-low latency, near-zero inference cost
  • Ops: Docker · Traefik · Hetzner
  • Fully decoupled frontend and backend
  • Knowledge base built from professional history and real projects
  • ~2 weeks part-time to a fully working system
04RESULTSThe Impact

Outcome:

vazquezdev.pro now behaves like a conversational assistant over curated professional context:

  • Self-hosted vector layer — no data leaves the server
  • Snappy inference via Groq with near-zero cost
  • Each layer of the stack evolves independently
SOL-02
CSR-Online
RAG · Enterprise · AI System
In Development
02

Enterprise Context AI

CSR-Online's leadership was drowning in disconnected sources. This system gives them one place to ask anything — and get answers backed by real data.

01SITUATIONThe Problem

Before this project:

There was no single place to ask a question and trust the answer. Leadership lived in three parallel worlds — Exchange mail, internal docs, and the operational SQL database — and “getting the full picture” meant opening all of them, paging the right person, and waiting. Strategic questions were answered late, partially, or from memory, because nobody could query everything at once without becoming the bottleneck themselves.

  • Every important answer required a scavenger hunt across mail, folders, and BI — not one search, not one thread
  • Executives depended on analysts and IT as human middleware between a question and the database
  • Knowledge went stale fast: the email was true last week, the doc said one thing, the live numbers said another
02OBJECTIVEThe Objective

Objective:

Give CSR-Online's leadership one natural-language interface over all company knowledge — email, files, and live database — without changing infrastructure or moving data to the cloud:

  • Single entry point for heterogeneous knowledge
  • Enterprise-scale vectors with Qdrant — self-hosted
  • SQL path when vector search alone isn't precise enough
03SOLUTIONThe Tech

Stack & highlights:

  • Core: Python · Qdrant
  • SQL Tool: Custom, LLM-callable routing to the operational DB
  • Email: Exchange on-premise · Journal (live) · PST ingestion (historical)
  • Ops: Docker
  • Hybrid RAG + SQL for maximum precision
  • Real-time email ingestion via Exchange Journal
04RESULTSThe Impact

Outcome:

A leadership-grade assistant built around CSR-Online's real constraints — on-premise, compliant, precise:

  • One query surface for mail, docs, and operational data
  • SQL precision when the LLM needs to hit the database directly
  • Centralized organizational memory that actually stays current
SOL-03
CSR-Online
Automation · n8n · AI Workflow
Live in Production
03

Telegram Reporting Agent

Sales reps were losing 1–2 hours per visit writing reports. Now they send a voice note and the system handles everything.

01SITUATIONThe Problem

The Problem:

After every client visit, sales reps spent 1–2 hours writing PDF reports by hand — formatting, attaching files, sending emails. The information was fresh right after the meeting; the bottleneck was transcription and bureaucracy. Selling time was being consumed by word processing.

  • 1–2 hours lost per report, per rep, after every single visit
  • Inconsistent formats depending on who wrote the report
  • Reports sent late — or skipped entirely — when the day got busy
02OBJECTIVEThe Objective

Objective:

Eliminate manual report writing entirely. A voice note or free-form text should be enough — the system produces a consistent, professional PDF and delivers it automatically:

  • Auto-detect five report types via Claude prompt design
  • Server archive plus automatic email delivery
  • Full chain: transcribe → classify → HTML → PDF → email → confirm
03SOLUTIONThe Tech

Stack & highlights:

  • Orchestration: n8n
  • Speech: Groq Whisper large-v3-turbo
  • Generation: Claude Sonnet 4.6 (HTML report)
  • PDF: Gotenberg
  • Mail: SMTP relay · Exchange on-premise
  • Infra: Docker · Hetzner
  • Built in 1 day — 6 active users from day one
04RESULTSThe Impact

Outcome:

A production workflow that pays back from the very first report:

  • ⚡ Built in 1 day; running in production at CSR-Online
  • 👥 6 active users — adopted without training
  • ⏱️ 1–2 hours saved per rep per report
  • ✅ Reps sell; the system handles the paperwork
SOL-04
Personal
Automation · n8n · AI Workflow
Live in Production
04

Invoice PDF Bot

Many solo operators still burn 20+ minutes per invoice across five tools. This flow replaces them with one Telegram message.

01SITUATIONThe Problem

The Problem:

Before automation, a typical freelance billing loop meant 20+ minutes per invoice: open accounting software, fill out forms, export the PDF, save to Drive, log it in a spreadsheet. A process you can describe in half a minute still required five tools and constant context-switching. At a few invoices a week, that overhead quietly eats a full workday every month.

  • 20+ minutes per invoice in repetitive, zero-value admin
  • Jumping between accounting UI, Drive, and Sheets on every single issue
  • Mental overhead of remembering to log, save, and file every invoice correctly
02OBJECTIVEThe Objective

Objective:

Let a solo freelancer issue compliant PDF invoices directly from their phone, with near-zero friction — one message in, one PDF out, everything filed automatically:

  • Parse messy natural language reliably every time
  • Deliver the PDF instantly back in Telegram
  • Keep Drive and Sheets automatically aligned for taxes and history
03SOLUTIONThe Tech

Stack & highlights:

  • Orchestration: n8n
  • Extraction & copy: Claude API
  • Channel: Telegram Bot API
  • Storage: Google Drive API · Google Sheets API
  • Infra: Docker · Hetzner
  • Full cycle: extract → PDF → Telegram → Drive → Sheets
04RESULTSThe Impact

Outcome:

Practical automation built for daily use — not a demo:

  • 📅 3–4 invoices per week in steady production use
  • ⚡ Built in 1 day; running in production
  • 📎 Every invoice traceable in Sheets and archived in Drive
  • 🎯 20 minutes → 30 seconds, every single time

>> // CAREER PATH _

From full-stack engineering to leading AI departments.

Full Stack Eng.2023
Backend & Data2024
AI Architect2025
AI LeadNOW
Mar 2026PRESENT
01
CURRENT FOCUS

Lead AI Architect & Developer

CSR Online·Mar 2026 - Present
  • Leading the company's AI department — defining strategy and executing end-to-end, from architecture to production.
  • Building internal AI systems and enterprise-grade solutions for the client portfolio.
  • Privacy-first: every system runs entirely on the client's own servers. No cloud dependency. Full compliance by design.
Oct 2025PRESENT
02
ACTIVE

AI Systems Architect & Developer

VazquezDev AI Solutions·Oct 2025 - Present
  • RAG systems for clients, workflow automations with n8n, and two AI-powered SaaS products currently in development.
  • Every project follows the same principle: production-ready, privacy-conscious, built to last.
  • The bridge between the developer I was and the AI architect I am.
Sep 2023Jan 2026
03
COMPLETED

Full Stack Engineer

VazquezDev·Sep 2023 - Jan 2026
  • Designed and delivered 4 end-to-end products — SaaS, mobile apps, and internal business tooling.
  • Full-cycle ownership: architecture, frontend, backend, containerization, and production delivery.
  • The foundation that now allows me to build and deploy AI systems end-to-end — not just the models, but the entire infrastructure.
20242025
04
COMPLETED

Backend & Data Infrastructure Engineer

  • Responsible for data integrity and speed in critical corporate environments. The technical foundation that ensures my current AI agents are robust and fail-safe.
  • SQL Optimization (High-Performance): 50% reduction in critical query latency (T-SQL), vital for current inference speed.
  • Security and Availability: Management of "Zero Data Loss" protocols in .NET/C# architectures.
  • Distributed Systems: Backend infrastructure maintenance for high availability during load peaks.
STACK INITIALIZED

// TECHNOLOGY STACK

Every tool chosen for a reason. No hype. No bloat. Just the stack that ships production-grade AI systems.

LAY-0107 TOOLS
The Engine

Infrastructure & Backend

Where business logic, data persistence and deployment live.

Django / FastAPIRobust backends and high-speed APIs
Node.jsHigh-performance asynchronous logic
PostgreSQLRelational databases for production workloads
MongoDBNoSQL for flexible document storage at scale
RedisSemantic caching and queue management
DockerContainerized deployment for stability
TraefikEdge router and reverse proxy for microservices
LAY-0207 TOOLS
The Brain

Orchestration & AI

The intelligence core. Long-context models, complex orchestration, autonomous agents.

PythonThe native language of AI infrastructure
LangGraph / LangChainGraph architecture for agents with memory, loops and conditional logic
LLMsGPT-5.4 · Claude Sonnet 4 · Gemini 3.1 Pro · Ollama / LLM Studio (local)
CrewAI / AutoGenCoordination of collaborative agent teams
Vector DatabasesChromaDB · Qdrant · pgvector — Semantic memory for RAG
n8nWorkflow automation and external tool connection
MCP ProtocolModel Context Protocol — connecting AI to local tools and systems
Foundation: TensorFlow · PyTorch · Scikit-learn · Hugging Face · MLflow
LAY-0306 TOOLS
The Interface

Human-Agent Interface

Modern interfaces for humans to supervise and control AI.

JavaScript / TypeScriptType-safe frontend development
Vue / Vuetify / NuxtEnterprise UI with SSR optimization and SEO-ready architecture
Tailwind CSSClean and responsive interface design
StreamlitRapid prototyping of internal AI tools
ChainlitConversational interfaces for AI agents
SupabaseBackend-as-a-Service with auth, storage and real-time
> DATA_FLOW:[ INFRASTRUCTURE ][ AI CORE ][ INTERFACE ]_
SYSTEMS ACTIVE

// GLOBAL REACH

Built to operate across markets, cultures and time zones.

SYS-0105 LANGUAGES
LANGUAGES
ES
EspañolNative
CAT
CatalàNative
EN
EnglishFull Professional
GL-PT
Galego-PortuguêsConversational · family roots
🇫🇷
FrançaisIn progress
SYS-02 ONLINE
BASE OF OPERATIONS
COORD:41.3874° N · 2.1686° E
Barcelona, Catalonia, Spain

One of Europe's top tech & startup hubs. Direct access to the Mediterranean innovation ecosystem.

GMT+1 Remote-first Available globally