Jobs and Careers
IR
AI ENGINEER SR – INGLES – REMOTO
IRIUMESPAÑA, ESPAÑA, SpainRemotefull_timeVerifiedPosted 19 Aug 2025
About the role
🚀 En IRIUM nos preocupamos porque no dejes de perseguir tus sueños. Prepárate para conquistar tus metas, y ten siempre presente disfrutar del camino. Estamos buscando un/a AI ENGINEER SR para un proyecto remoto.
🔍 ¿Qué buscamos?:
RESPONSIBILITIES
• Lead the technical design and development of an AI-powered multi-agent system deployed on AWS, with RAG pipelines, LLM guardrails, and external service integrations.
• Define the overall architecture and agent strategy, ensuring modularity, scalability, and traceability of AI decision processes.
• Guide the development and orchestration of agents responsible for knowledge retrieval (RAG), ticket r esolution, API interaction (e.g., SharePoint), and user interaction flows.
• Oversee the integration of vector search mechanisms, memory systems, and retrieval pipelines over internal document repositories.
• Define standards for LLM safety, grounding, and guardrails, and supervise the implementation of mitigation strategies.
• Collaborate with DevOps, Frontend, and Backend teams to ensure infrastructure, UI, and APIs align with AI requirements.
• Review and validate experimental results, fine-tune model behaviors, and supervise performance evaluation pipelines.
• Mentor AI engineers, coordinate tasks within the AI team, and contribute to roadmap definition and delivery planning.
• Serve as the main technical referent in AI, ensuring best practices, documentation, and maintainability.
TECHNOLOGY STACK
• AI & Agent Orchestration: Python, LangChain, CrewAI, Semantic Kernel, OpenAI API, Claude, local LLMs (e.g., Llama2, Mistral)
• RAG & Vector DBs: FAISS, Weaviate, Qdrant, Pinecone, AWS Kendra
• Guardrails & Safety: Guardrails AI, LlamaIndex, prompt validation tools
• Cloud Platform: AWS (Lambda, S3, API Gateway, Cognito, SageMaker/AzureML optional)
• APIs & Integration: REST APIs, SharePoint Graph API, JSON schemas
• Experiment Tracking & Observability: MLflow, Weights & Biases, CloudWatch, custom dashboards
• Collaboration: Confluence, Jira, Git
REQUIREMENTS
• Proven experience designing and implementing LLM-based systems, including multi-agent architectures and retrieval-augmented generation (RAG) pipelines.
• Strong background in AI system architecture, with hands-on experience in agent orchestration frameworks and prompt engineering.
• Deep understanding of LLM safety, hallucination mitigation, and implementation of guardrails.
• Solid knowledge of vector search, embedding models, and knowledge base retrieval strategies.
• Experience working with AWS-based ML pipelines and integrating with enterprise systems (e.g., SharePoint).
• Demonstrated ability to lead technical teams, mentor peers, and drive AI initiatives from design to production.
• Strong coding skills in Python and familiarity with modern LLM APIs and tools.
• Fluent in English (spoken and written); Spanish is a plus.
• Background in Artificial Intelligence, Machine Learning, or related technical fields.
⭐ ¿Qué Ofrecemos?
🔍 ¿Qué buscamos?:
RESPONSIBILITIES
• Lead the technical design and development of an AI-powered multi-agent system deployed on AWS, with RAG pipelines, LLM guardrails, and external service integrations.
• Define the overall architecture and agent strategy, ensuring modularity, scalability, and traceability of AI decision processes.
• Guide the development and orchestration of agents responsible for knowledge retrieval (RAG), ticket r esolution, API interaction (e.g., SharePoint), and user interaction flows.
• Oversee the integration of vector search mechanisms, memory systems, and retrieval pipelines over internal document repositories.
• Define standards for LLM safety, grounding, and guardrails, and supervise the implementation of mitigation strategies.
• Collaborate with DevOps, Frontend, and Backend teams to ensure infrastructure, UI, and APIs align with AI requirements.
• Review and validate experimental results, fine-tune model behaviors, and supervise performance evaluation pipelines.
• Mentor AI engineers, coordinate tasks within the AI team, and contribute to roadmap definition and delivery planning.
• Serve as the main technical referent in AI, ensuring best practices, documentation, and maintainability.
TECHNOLOGY STACK
• AI & Agent Orchestration: Python, LangChain, CrewAI, Semantic Kernel, OpenAI API, Claude, local LLMs (e.g., Llama2, Mistral)
• RAG & Vector DBs: FAISS, Weaviate, Qdrant, Pinecone, AWS Kendra
• Guardrails & Safety: Guardrails AI, LlamaIndex, prompt validation tools
• Cloud Platform: AWS (Lambda, S3, API Gateway, Cognito, SageMaker/AzureML optional)
• APIs & Integration: REST APIs, SharePoint Graph API, JSON schemas
• Experiment Tracking & Observability: MLflow, Weights & Biases, CloudWatch, custom dashboards
• Collaboration: Confluence, Jira, Git
REQUIREMENTS
• Proven experience designing and implementing LLM-based systems, including multi-agent architectures and retrieval-augmented generation (RAG) pipelines.
• Strong background in AI system architecture, with hands-on experience in agent orchestration frameworks and prompt engineering.
• Deep understanding of LLM safety, hallucination mitigation, and implementation of guardrails.
• Solid knowledge of vector search, embedding models, and knowledge base retrieval strategies.
• Experience working with AWS-based ML pipelines and integrating with enterprise systems (e.g., SharePoint).
• Demonstrated ability to lead technical teams, mentor peers, and drive AI initiatives from design to production.
• Strong coding skills in Python and familiarity with modern LLM APIs and tools.
• Fluent in English (spoken and written); Spanish is a plus.
• Background in Artificial Intelligence, Machine Learning, or related technical fields.
- RESIDENCIA EN ESPAÑA
- INGLES: Mínimo B2
⭐ ¿Qué Ofrecemos?
- Lugar de trabajo: REMOTO – RESIDENCIA EN ESPAÑA
- Contrato indefinido con IRIUM
- Retribución flexible <
Apply for this role
Generate a tailored application kit with a matched cover letter, interview prep, and CV highlights — in under 60 seconds.
Apply Now →Generate Application KitFree account required — sign up in 30s