Principal MLOps Engineer
Lea el resumen de esta oportunidad para comprender qué habilidades, incluidas las habilidades interpersonales relevantes y el dominio de paquetes de software, se requieren.
Location: Remote from Spain (Spanish employment contract)
We are looking for Principal MLOps Engineer to support the development of AI-driven solutions in Global Digital Marketing team of a Leading Agricultural Company. The engineers will work on projects involving generative AI, intelligent agents, and process automation, integrating with large-scale enterprise systems. The current goals are to create two LLM agents, that are responsible for producing marketing Campaigns materials – campaign information, images, presentations, slogans, etc.
Requirements:
Proven experience in developing and deploying generative AI or LLM-based applications
Participate on the architectural design of conversational solutions.
Strong prompt proficiency with LLMs such as OpenAI, Azure OpenAI, Claude, or LLaMA
Hands-on experience with LangChain, LangGraph. Other frameworks are also valued.
Solid understanding of semantic search, RAG pipelines, and vector embeddings
AWS experience with ECR, ECS/Fargate and dockerization.
Design/Deploy MCP servers.
Background in API/microservices development
Ability to work with enterprise-grade architectures and process automation tools
English: at least B2 level.
Will be a plus:
Experience with n8n, Semantic Kernel, Copilot Studio,
Experience with MLOps, model optimization, and cloud deployments (especially AWS)
Previous experience with digital marketing life cycle. xohynlm
SQL proficiency
Expertise using Claude Code, GitHub copilot and similar tools as part of their daily tooling, working routines
Responsibilities:
Lead the development of LLM-based intelligent agents
Prepare system architecture, agree system design with stakeholders
Contextualization of the company data.
Implement Retrieval-Augmented Generation (RAG) systems
Integrate LLMs with varius different data sources
Leverage tools like LangChain, LangGraph, Semantic Kernel, and Copilot Studio to build semantic workflows
Automate internal processes using n8n
Collaborate with cross-functional teams including DevOps, backend, and business stakeholders
Contribute to best practices for AI deployment, prompt engineering, and model evaluation