LLM Engineer — Production AI & RAG Pipelines (Hybrid)

Capitole; Barcelona; Híbrido; EUR 55.000 - 75.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Hybrid work model (2 days onsite per週)

Private health insurance

€1200 per year training budget

Team buildings and events

Wellhub: fitness, wellness and mental

Flexible working hours

Descripción de la vacante

Capitole in an international tech environment seeks an AI Engineer to design, build, and deploy LLM-powered apps, RAG pipelines, and multi‑agent systems on AWS.

You will collaborate with Data Scientists, Platform/DevOps, and Product Managers to move AI solutions from experimentation to production using Python, FastAPI, Docker, and Kubernetes.

Hybrid work model (2 days onsite weekly) with a focus on scalable AI, evaluation frameworks, and strong engineering practices.

Formación

• 3–5 years software engineering with 1–2 years in AI/ML
• Strong Python proficiency
• Experience with LangChain/LangGraph and ML frameworks
• Hands-on RAG systems and vector stores
• Experience with LLM APIs such as AWS Bedrock/OpenAI/Anthropic
• Knowledge of prompt engineering and evaluation
• Experience with Docker and Kubernetes
• Experience with Airflow/Prefect
• Experience shipping production AI solutions
• Spanish language skills a plus

Responsabilidades

• Design, build, and maintain LLM-powered applications and multi-agent systems using LangGraph/LangChain
• Develop and optimise RAG pipelines, embeddings, and retrieval logic
• Implement and manage vector databases on Aurora/OpenSearch/Pinecone
• Build and maintain data and ETL pipelines with Airflow/Prefect
• Develop backend services and APIs in Python/FastAPI to serve AI models and workflows
• Deploy and manage AI workloads on AWS Bedrock, SageMaker, Lambda, S3, Aurora/RDS
• Work with Docker and Kubernetes to containerise and orchestrate workloads
• Collaborate with domain experts and product managers to turn business needs into AI solutions
• Participate in Scrum ceremonies and contribute to Agile culture
• Stay up to date with AI/ML ecosystem and propose improvements

Conocimientos

Python

LangChain

LangGraph

Hugging Face

PyTorch

AWS Bedrock

RAG pipelines

Docker

Kubernetes

FastAPI

Herramientas

CrewAI

pgvector

Aurora

OpenSearch

Pinecone

Apache Airflow

Prefect

FastAPI

Docker

Descripción del empleo

Capitole in an international tech environment seeks an AI Engineer to design, build, and deploy LLM-powered apps, RAG pipelines, and multi‑agent systems on AWS.

You will collaborate with Data Scientists, Platform/DevOps, and Product Managers to move AI solutions from experimentation to production using Python, FastAPI, Docker, and Kubernetes.

Hybrid work model (2 days onsite weekly) with a focus on scalable AI, evaluation frameworks, and strong engineering practices.