AI / Data Platform Engineer (Knowledge Bases, Graph & GenAI)

🛠️ Essential requirements

• Advanced Python.

• Advanced SQL.

• Experience in software development, Data Engineering, or AI Engineering.

• FastAPI.

• REST API development.

• Asynchronous programming.

• Performance optimization.

• PostgreSQL.

• Amazon Aurora PostgreSQL.

• Schema design and query optimization.

Real experience with:

• Graph Databases.

• Cypher.

• Gremlin.

• SPARQL.

• Graph modeling.

Experience in:

• AWS (highly valued).

• Azure.

Experience with:

• AWS Bedrock.

• LLMs.

• Prompt Engineering.

• RAG Systems.

• Docker.

• Git.

• CI/CD.

⭐ Highly valued

• Amazon Neptune.

• Advanced graph design.

• GraphRAG architectures.

• LangChain.

• LangGraph.

• LlamaIndex.

• Databricks.

• Spark.

• Kafka.

• Streaming.

• Kubernetes.

• Terraform.

• Cloud Native architectures.

• Multi-agent systems.

• Semantic Modeling.

• Ontologies.

• Data Virtualization.

• Federated Query Systems.

• OCR.

• Document processing.

• Information extraction.

• Multimodal processing.

• Analyst (2-3 years experience): up to €35,000 SBA

• Consultant (3-5 years experience): up to €45,000 SBA

🎯 Job Objective

We are looking for 3 technical AI / Data Platform Engineer profiles to participate in a strategic initiative focused on building enterprise knowledge platforms based on:

• Knowledge Bases

• Knowledge Graphs

• Semantic Layers

• GenAI

• RAG

• Semantic search

• Intelligent exploitation of corporate data

The project is oriented towards creating advanced capabilities for accessing and exploiting structured and unstructured information within a highly regulated banking environment.

🚀 Main responsibilities

• Design and development of pipelines for creating and maintaining knowledge bases.

• Construction of semantic layers for enterprise information exploitation.

• Design and implementation of knowledge graphs (Knowledge Graphs).

• Development of pipelines for vector databases and semantic retrieval.

• Implementation of RAG (Retrieval Augmented Generation) solutions.

• Integration of LLM models into production environments.

• Development of semantic search capabilities and intelligent information retrieval.

• Implementation of Text-to-SQL functionalities.

• Construction of AI-based intelligent assistants.

• Development of REST APIs with FastAPI.

• Construction of corporate knowledge access services.

• Performance and scalability optimization of services.

Integration of enterprise sources such as:

• Data Lakes

• Amazon S3

• SharePoint

• FileNet

• Corporate document repositories

• Relational and non-relational databases

• Observability and monitoring.

• Quality controls.

• Human-in-the-loop workflows.

• Security and scalability.

• Deployment automation.

📍 Location: Madrid (preferred) or Málaga
🏢 Modality: Hybrid (1-2 days in office per week)

We are looking for profiles with between 2 and 5 years of real experience in one of these areas:

• LLMs

• RAG

• GenAI

• LangChain

• Bedrock

• Python

• SQL

• Databricks

• Spark

• Kafka

• Neo4j

• Neptune

• Cypher

• SPARQL

• Gremlin

• AWS

• Kubernetes

• Docker

• Terraform

• DevOps