Generative AI Engineer | LLMs, RAG and Multi-agent Systems

knowmad moodMadridJob.bopublished 09/28/2026
Must-have:PythonGitAWSAzureGoogle CloudDockerCloudCI/CDAI
Machine translation — original language: Spanish.Show original

We are knowmad mood! We are a leading company in digital transformation, constantly evolving and at the forefront of technology. We were born to provoke real change through innovation and sustainable development, with the mission of providing value to clients and driving our talent. Comprised of more than 3,000 creative, digital, and innovative people connected to a purpose and capable of generating connections with people all over the world. A responsible, flexible team with a high capacity to adapt to the needs of our clients and the market, while providing value, vision, creativity, expertise, professionalism, and passion for technology in every project. The values that mark our course and guide us toward excellence are collaboration, innovation, commitment, fun, and trust. What do we value? At least 3 years of experience in software development, platform engineering, or distributed systems.

  • Solid experience in software development with Python.
  • Practical knowledge and demonstrable experience with Generative Artificial Intelligence, Large Language Models (LLMs), and AI-based enterprise applications.
  • Experience in the design and implementation of RAG (Retrieval-Augmented Generation) architectures.
  • Experience developing and integrating APIs and microservices.
  • Knowledge of relational and NoSQL databases.
  • Experience working with Docker, Git, and CI/CD environments.
  • Experience in incident resolution and troubleshooting in production environments.
  • Knowledge of observability, monitoring, logging, traceability, and metrics.
  • Ability to work in agile and multidisciplinary environments.
  • English level B2 or higher, in an international technical environment.
  • Analytical capacity, orientation toward quality, and a continuous improvement mindset.

What would your functions be?

  • Design, develop, and deploy AI agents for business use cases.
  • Implement solutions based on LLMs, RAG architectures, and multi-agent systems.
  • Integrate intelligent agents with corporate applications and systems through APIs and services.
  • Ensure the stability, scalability, resilience, and performance of deployed solutions.
  • Monitor agent behavior and define observability mechanisms that allow for correct operation in production.
  • Analyze incidents in production environments, perform troubleshooting, and execute Root Cause Analysis.
  • Optimize prompts, execution flows, token consumption, and utilization of foundational models.
  • Collaborate closely with architects, platform teams, and business areas in the evolution of the AI platform.
  • Participate in the industrialization of AI solutions, taking use cases from proof of concept to production environments.
  • Contribute to the definition of standards, best practices, and operating models for the development and deployment of Generative Artificial Intelligence solutions.

Additionally, we will highly value if you have experience and/or knowledge in:

  • Agent frameworks such as LangChain, LangGraph, Semantic Kernel, CrewAI, or AutoGen.
  • Multi-agent systems and agentic workflows.
  • Azure AI Services, Azure OpenAI, AWS Bedrock, or Vertex AI.
  • Vector databases, embeddings, and semantic search.
  • Observability tools such as OpenTelemetry, Grafana, Prometheus, Jaeger, or Elastic Stack.
  • Design and construction of scalable AI platforms.
  • Integration patterns through tool calling and function calling.
  • MLOps, AIOps, and AI platform automation.
  • Cloud Certifications (Azure, AWS, or GCP).
  • Previous experience working on international projects.

And with us you will be able to enjoy:

  • Joining a strategic project for the evolution of a Generative Artificial Intelligence platform for enterprise environments.
  • Participation in innovative initiatives related to intelligent agents, multi-agent systems, and LLM-based platforms.
  • Hybrid work model with 1 or 2 days of teleworking per week.
  • Flexible start time between 07:00 and 10:00.
  • Full-time schedule of 8 hours daily and 1 hour for lunch.
  • Approximately 30 business days of vacation per year, compensating for the absence of an intensive workday.
  • Location: Madrid.

To stay up to date with our news follow us here -> knowmad mood At knowmad mood, we are committed to equal opportunities and respect for diversity. We apply our Equality Plan and the principle of non-discrimination in all our selection processes.