AI Engineer – Search, Vector Databases & RAG | Madrid (Hybrid)

TrioTech Recruitment; Madrid; Híbrido; EUR 50.000 - 70.000; Jornada completa

Descripción de la vacante

A fast-growing tech company is seeking an AI Engineer to drive advancements in search technologies and build intelligent workflows. This position entails designing search pipelines, optimizing RAG systems, and ensuring robust knowledge retrieval. The ideal candidate should have strong experience with vector search and RAG systems, proficient in Python, and open to hybrid working within Madrid. Join a dynamic product team and make an impactful contribution to enterprise solutions.

Formación

• Strong experience with vector search technologies like Pinecone, Weaviate, Milvus, or Elasticsearch.
• Hands-on experience in building RAG systems in production environments.
• Solid background in software engineering, preferably with Python.

Responsabilidades

• Design advanced search pipelines using vector databases.
• Build and optimize RAG-based systems for performance.
• Collaborate with cross-functional teams to ship features.

Conocimientos

Vector search technologies

RAG systems building

Software engineering (Python)

LLMs and embeddings familiarity

Scalable search systems design

Descripción del empleo

I’m supporting a fast-growing tech company that is building a next‑generation search and intelligence layer for their platform. We’re looking for an AI Engineer with deep experience in search technologies, vector databases, and Retrieval-Augmented Generation (RAG).

This role sits in a high‑impact product team working on a new initiative, with the freedom to shape architecture, improve search relevance, and build intelligent workflows used by thousands of enterprise users.

What you’ll work on

• Designing and implementing advanced search pipelines using vector databases and embeddings
• Building and optimising RAG‑based systems for retrieval quality, latency, and scalability
• Developing internal tools and services that improve knowledge retrieval and search discovery
• Collaborating with product, data, and engineering teams to ship features end‑to‑end
• Evaluating new LLMs, embedding models, and retrieval techniques for production use

Must Have

• Strong experience with vector search (e.g., Pinecone, Weaviate, Milvus, Elasticsearch, OpenSearch)
• Hands‑on experience building RAG systems in production
• Solid software engineering background (Python preferred)
• Familiarity with LLMs, embeddings, prompt engineering, and optimisation techniques
• Experience designing scalable search systems or AI‑driven knowledge retrieval pipelines
• Based in (or willing to relocate to) Madrid; hybrid working environment (3 Days onsite)

Nice to have

• Experience with ranking models, semantic search, and relevance tuning
• Knowledge of cloud platforms (AWS, Azure, or GCP)
• Previous work on internal developer tools or productivity / observability products