ppWe are looking for an bAI Engineer /b to join a dynamic AI team within an international technology environment. /ppIn this role, you will design, build, and deploy bLLM-powered applications, RAG pipelines, multi-agent systems, and scalable AI solutions /b on AWS. /ppYou will work at the intersection of bsoftware engineering, AI engineering, data pipelines, and cloud deployment /b, contributing to real use cases across the group. This role is highly hands-on and focused on building intelligent systems that move from experimentation to production. /ppYou will work closely with Data Scientists, Platform and DevOps Engineers, Data Engineers, domain experts, Product Managers, and the Tech Lead to move AI solutions from experimentation into production. /ppIf you enjoy working with bLLMs, agents, RAG, vector databases, Python APIs, and AWS-native AI services /b, this could be a great fit. /ph3What you’ll do /h3ulliDesign, build, and maintain bLLM-powered applications /b and multi-agent systems primarily using bLangGraph /b and bLangChain /b, alongside tools such as CrewAI or similar frameworks /liliDevelop and optimise bRAG pipelines /b, including document ingestion, chunking strategies, embedding generation, retrieval logic, and vector search /liliImplement and manage vector databases such as bpgvector on Aurora, OpenSearch, Pinecone /b, or similar /liliBuild and maintain data and ETL pipelines using bApache Airflow, Prefect /b, or similar tools /liliDevelop backend services and APIs in bPython / FastAPI /b to serve AI models, RAG systems, and agent workflows /liliDeploy and manage AI workloads on bAWS /b services such as bBedrock, SageMaker, Lambda, S3, Aurora/RDS, EC2 /b /liliWork with bDocker and Kubernetes /b to containerise and orchestrate AI workloads /liliDesign and execute evaluation frameworks for LLM outputs, including automated testing, LLM-as-judge approaches, and human-in-the-loop review /liliWork with LLM APIs and orchestration tools such as bAWS Bedrock, OpenAI API, Anthropic API /b, or similar /liliApply prompt engineering and LLM evaluation methodologies,



and assess when fine-tuning or other adaptation techniques are appropriate. /liliCollaborate with domain experts, Data Engineers, Product Managers, and the Tech Lead to turn business requirements into AI solutions /liliParticipate in Scrum ceremonies and contribute to a collaborative Agile engineering culture /liliStay up to date with the rapidly evolving AI/ML ecosystem and proactively propose new tools, improvements, and approaches /liliSupport less experienced team members and share AI engineering best practices across the team. /lilib3–5 years of experience in Software Engineering /b, with at least b1–2 years focused on AI / ML Engineering /b /liliStrong proficiency in bPython /b /liliExperience with AI/ML and LLM frameworks such as bLangChain, LangGraph, Hugging Face, PyTorch /b, or similar /liliHands-on experience building bRAG systems /b, including embeddings, vector stores, semantic search, and hybrid search strategies /liliExperience working with bLLM APIs /b such as bAWS Bedrock, OpenAI API, Anthropic API /b, or similar /liliSolid understanding of bprompt engineering, fine-tuning techniques, and LLM evaluation methodologies /b /liliHands-on experience with bAWS /b services such as bEC2, S3, Lambda, Aurora/RDS, Bedrock, SageMaker /b /liliExperience with observability and evaluation platforms for LLMs such as bLangfuse, Datadog LLM Observability, LangSmith /b /liliExperience with bDocker and Kubernetes /b /liliFamiliarity with data pipeline tools such as bApache Airflow, Prefect /b, or similar /liliExperience developing backend services or APIs, ideally with bFastAPI /b /liliProficiency with bGit /b and software engineering best practices /liliExperience working in a bScrum Agile /b environment /liliStrong problem-solving,



analytical thinking, communication, and teamwork skills /liliExperience with bmulti-agent architectures /b and protocols such as bA2A or MCP /b /liliFamiliarity with MLOps practices: model versioning, experiment tracking, MLflow, Weights Biases, and CI/CD for ML /liliKnowledge of graph databases or knowledge graphs for enhanced retrieval /liliExperience with CI/CD pipelines using tools such as bGitHub Actions /b /liliFamiliarity with Infrastructure as Code, especially bTerraform /b /liliExperience with code quality and security tools such as bSonarCloud, Snyk /b /liliExperience in aviation, travel, or large-scale digital environments /liliSpanish language skills are a plus /li /ulpHybrid model - 2 days onsite per week /ph3Why join this project? /h3ulliPeople first – diverse and inclusive culture in an international environment. /liliBuild production-ready LLM applications, RAG systems, and agentic AI solutions /liliWork with cutting-edge AI technologies across the LLM, agents, vector search, and AWS ecosystem /liliContribute to scalable engineering practices around AI applications, data pipelines, evaluation, and deployment /liliGain hands-on exposure to AWS-native AI services such as Bedrock, SageMaker, Lambda, S3, and Aurora /liliBe part of a fast-moving AI environment where experimentation, ownership, and impact are highly valued /liliHigh team stability and collaborative culture. /lili€1200 per year training budget and continuous learning opportunities. /liliPrivate health insurance and benefits package. /liliFlexible working hours and hybrid model. /liliWellhub: fitness, wellness, and mental health support. /liliFootball and paddle tennis teams sponsored by Capitole. /liliTeam buildings, general events, and strong tech communities. /li /ulpInformation Security Notice /ppThe employee will have access to confidential information related to Capitole and the assigned project. /ppCompliance with internal security and information protection policies is mandatory. /p /p #J-18808-Ljbffr

📌 AI Engineer (Barcelona)
🏢 Capitole
📍 Barcelona