Applied AI and Infrastructure Engineer

Description

**We are looking for IT talent specialized in Artificial Intelligence and infrastructure!** At Grupo PROEDUCA, a leader in online higher education, we are seeking to hire an **Applied AI and Infrastructure Engineer** to join our technology team and participate in the construction, deployment, and operation of production-ready Artificial Intelligence systems. We seek a **builder** profile—someone capable of taking an idea from proof-of-concept to a real, stable, and scalable system. A professional with solid applied AI knowledge and a strong technical foundation in infrastructure, DevOps, and cloud, who enjoys building solutions and taking ownership of their operation in production. You will join an environment where Artificial Intelligence is central to new products and services, working with modern technologies such as LLMs, agents, RAG, Kubernetes, Docker, and real-time voice platforms. **What will you do on a day-to-day basis?** * Design and build AI systems based on **LLMs and agents**, working on agent orchestration, tool usage, memory, and error recovery mechanisms. * Create **agent-based platforms** and multi\-agent systems ready for production environments, incorporating orchestration, tools, memory, sandboxing, and security. * Design and develop **real-time voice platforms** using LiveKit, WebRTC/SIP, Kubernetes, and traditional voice pipelines based on STT \+ LLMs \+ TTS. * Design **RAG systems** and participate in model adaptation via fine\-tuning when it adds value to the domain and use case. * Build and consume **REST APIs** to expose AI systems and integrate them with our data sources and internal services. * Containerize and deploy services using **Docker and Kubernetes**, working with Dockerfiles, manifests, and deployments across clusters. * Automate infrastructure using **CI/CD and Infrastructure-as-Code**, leveraging tools like Terraform to create reproducible environments. * Operate and monitor deployed systems using metrics, logs, and traces, designing solutions focused on **observability, reliability, and scalability**. * Prototype new ideas in short sprints: hypothesis formulation, architecture definition, development, and creation of functional demos. * Write clean, maintainable, tested, and observable code, actively participating in the team’s code reviews. **What are we looking for?** * Demonstrable experience of **3–5 years building AI systems in production**, with proven ability to take solutions from prototype to production environments. * Solid knowledge of **LLMs**, including prompting techniques, skill generation, and MCP construction and integration. * Experience designing **RAG systems**, including chunking, embeddings, vector databases, and integration with language models. * Experience building **agent-based systems** using frameworks such as LangGraph, CrewAI, AutoGen or similar, as well as orchestrating them. * Strong **Python** skills, with the ability to write organized, maintainable, and tested code. * Solid knowledge of **infrastructure and DevOps**: Docker, CI/CD, Git, and Linux command line. * Experience designing and consuming **REST APIs**, using FastAPI, Flask, or equivalent technologies. * DevOps mindset and operational orientation: ability to work not only at the application layer but also on deployment, maintenance, and evolution of systems. * Professional-level Spanish and **sufficient English to work with technical documentation and libraries**. Bonus points for: * Experience with **Infrastructure-as-Code**, especially Terraform, Ansible, or equivalent tools. * Knowledge of **cloud platforms** (AWS, Azure, or GCP), particularly compute, storage, and networking services. * Experience in **observability**, using tools such as Prometheus, Grafana, and various logging and tracing stacks. * Knowledge of **GitOps, Helm, and deployment automation**. * Experience in **LLM evaluation and observability**, including evals, quality metrics, and hallucination detection. * Experience with **vector databases**, such as pgvector, Pinecone, Weaviate, Qdrant, or similar. * Familiarity with **MLOps and AI-oriented data pipelines**. * Experience in **model fine\-tuning**, including techniques such as SFT, LoRA, or equivalents. * Personal projects, open-source contributions, or a technical portfolio on GitHub. **What do we offer?** ✅ Permanent contract within a leading, continuously growing educational group. Hybrid work model and flexible working hours. Join a team working with **applied AI in real production scenarios**, within an expanding company. Work with modern technologies: Applied Artificial Intelligence, LLMs, agents, containers, Kubernetes, and cloud. Development and continuous training plan, with access to our educational platforms. Competitive salary aligned with experience and expertise. A technological environment where you can contribute to real projects and assume responsibility for the solutions you build. **We want to meet you!** If you are passionate about **applied Artificial Intelligence**, enjoy building solutions that reach production, and want to work at the intersection of AI, engineering, and infrastructure—this is your opportunity! *The EDUCATIONAL GROUP is firmly committed to equal opportunities and diversity, thereby creating an environment free from all forms of discrimination.* \#LI\-SP1 Group companies Management and Administration Staff (PGA) Position Technology Locations Madrid \- Spain Remote status Hybrid Employment type Full-time Company PROEDUCA \- Globalpro