Context And Mission

The AI Factory is expanding its portfolio of generative AI services and solutions to support researchers, public institutions, startups, SMEs, and industry partners in adopting artificial intelligence effectively and responsibly.
To accelerate the delivery of these services, we are looking for an AI Engineer – Generative AI Solutions who will transform validated AI concepts into robust, scalable, and production-ready applications. The role combines strong software engineering capabilities with expertise in large language models, retrieval systems, AI agents, and modern AI application architectures.
Working closely with AI engineers, project managers, domain experts, and platform teams, the successful candidate will design, build, deploy, and maintain generative AI solutions that deliver measurable value to end users while ensuring reliability, security, observability, and operational excellence.
The mission of this role is to bridge the gap between AI experimentation and real-world adoption by creating trustworthy AI products and reusable technical components that accelerate future AI initiatives across the AI Factory ecosystem.

Key Duties

- - Design, develop, and maintain production-ready generative AI applications and services.
- Build APIs, backend services, integrations, and user-facing AI functionalities.
- Implement Retrieval-Augmented Generation (RAG) pipelines, prompt orchestration frameworks, tool calling mechanisms, and agent-based workflows.
- Design and optimize context management strategies, including embeddings, semantic retrieval, grounding, memory management, and knowledge integration.
- Evaluate and improve AI system performance in terms of accuracy, reliability, latency, safety, scalability,



and cost efficiency.
- Integrate AI solutions with enterprise platforms, internal systems, authentication mechanisms, and external data sources.
- Implement monitoring, observability, logging, tracing, guardrails, and operational controls for AI services.
- Develop reusable software components, frameworks, templates, and best practices to accelerate AI solution delivery.
- Collaborate with AI engineers, researchers, project managers, and business stakeholders to translate requirements into technical solutions.
- Contribute to the definition of AI engineering standards, software architecture guidelines, and operational procedures.
- Support deployment, testing, troubleshooting, and continuous improvement of AI services throughout their lifecycle.
- Produce and maintain technical documentation for developed solutions, architectures, and operational processes.

Requirements

- Education
- Bachelor's or Master's degree in Computer Science, Software Engineering, Artificial Intelligence, Data Science, Telecommunications Engineering, Mathematics, Physics, or a related technical discipline.

- Essential Knowledge and Professional Experience

- - 3–5 years of experience in software engineering, backend development, or AI application development.
- 2+ years of hands-on experience developing solutions based on Large Language Models (LLMs)



and Generative AI technologies.
- Proven experience building and deploying production-grade applications using - - Python and modern software development practices.
- Experience with Retrieval-Augmented Generation (RAG), vector databases, embeddings, semantic search, and knowledge retrieval systems.
- Experience designing and implementing APIs, microservices, and system integrations.
- Knowledge of AI orchestration frameworks and agent-based architectures LangChain, LlamaIndex, Semantic Kernel, CrewAI, AutoGen, or similar).
- Experience working with cloud platforms and AI services (AWS, Azure, Google Cloud, OpenAI, Anthropic, or equivalent).
-Experience with software testing, observability, monitoring, logging, and production support.
- Understanding of LLM evaluation methodologies, prompt engineering, model limitations, hallucination risks, and AI quality assurance.
- Experience working with Git, CI/CD pipelines, containerization technologies (Docker), and modern software delivery practices.
- Strong analytical and problem-solving skills, with the ability to translate business or research requirements into technical solutions.
- Experience working in multidisciplinary teams within research, innovation, technology, or product development environments.

- Additional Knowledge and Professional Experience

- - Experience deploying AI solutions in enterprise, scientific, research, or public-sector environments.
- Familiarity with MLOps, LLMOps, AI governance, responsible AI, and AI security practices.
- Experience with multi-agent systems and autonomous AI workflows.
- Exposure to HPC, distributed comp

📌 AI Engineer – Generative AI Applications (Barcelona)
🏢 Barcelona Supercomputing Center
📍 Barcelona