Xavier
Mareca

Data & AI Consultant

Practical data and AI systems. Without the hype.

LinkedIn GitHub Email
0
Years in BI
0
Projects Delivered
0
AI Apps Built
0
EU Languages
Background

8 years reading data.
Now teaching machines to do it.

I started in BI — Power BI, DAX, semantic models, enterprise dashboards. Then in 2022 I went deep into AI: LangChain, RAG pipelines, SageMaker, multi-agent systems. Not a pivot. An extension. I now build data systems where the BI layer and the AI layer actually talk to each other.

AI & LLMs
RAG pipelines, LangChain, CrewAI agents, Anthropic Claude integrations.
Cloud Engineering
AWS SageMaker, Lambda, Step Functions — serverless, event-driven architectures.
Business Intelligence
Advanced DAX, semantic models, high-performance Power BI analytics.
Spanish · French · English · German · LinkedIn · XDT.AI

Current focus

AWS MLA-C01 · DP-700
ML Engineering + Microsoft Fabric — dual exam track, 2026
In Progress
Multi-Agent Systems
CrewAI and LangGraph for complex AI workflows
Researching
Anthropic Claude Integration
Production RAG systems with LangChain and ChromaDB
Completed
Work

Selected projects

AI-Powered BI Assistant

PORTFOLIO

Natural language querying over structured data. RAG pipeline with full test suite — 86 integration tests with pytest.

LangChain RAG Claude FastAPI ChromaDB
v1.0.0
• Handles complex JOINs and aggregations
• CI/CD with GitHub Actions

HR RAG Assistant

PORTFOLIO

Multi-turn conversational assistant over HR policy documents. Session memory, automatic re-indexing on document updates.

LangChain ChromaDB Claude FastAPI GitHub Actions
CI/CD
• ConversationalRetrievalChain with memory
• Docker + GitHub Actions pipeline

Sales Analytics Pipeline

PORTFOLIO

End-to-end pipeline from multiple sources to Power BI dashboards. PySpark + Delta Lake + star schema.

PySpark Delta Lake Power BI Azure
Medallion arch.
• Bronze / Silver / Gold layers
• Incremental refresh in Fabric

Document Intelligence

PORTFOLIO

Automated extraction from unstructured documents using Claude + AWS Textract. JSON output with confidence scores.

Claude Python AWS Textract S3
Structured output
• Serverless on AWS Lambda
• Confidence scoring per field

Serverless Data Pipeline

PORTFOLIO

Event-driven architecture on AWS. Lambda + EventBridge + DynamoDB + API Gateway — SageMaker lab series.

AWS Lambda DynamoDB SageMaker
7 labs
• Model Monitor + drift detection
• Step Functions orchestration

Tech stack

Business Intelligence
Power BI
DAX
SQL Server
Semantic Models
AI & Agents
CrewAI
LangChain
Anthropic Claude
RAG
Ollama
Vector DBs
Data Engineering
PySpark
Delta Lake
Databricks
SQL
Python
Pandas
Cloud & APIs
Azure
AWS
Microsoft Fabric
FastAPI
Docker
GitHub Actions