Experteer Overview
¿Es este su próximo empleo? Descúbralo leyendo la descripción completa a continuación y no dude en enviar su candidatura.
In this role you design, build, and deploy production-grade agentic AI systems for enterprise clients. You will work with client engineering teams, lead architectural design discussions, and create reusable patterns that scale beyond individual engagements. You’ll shape governance, observability, and LLM orchestration across multi-LLM environments, driving measurable AI impact for businesses. This opportunity combines breadth across industries with access to leading AI programs and deployment pathways.
Compensaciones / Ventajas
• Architect production-grade agentic systems at enterprise scale, including multi-agent orchestration, RAG pipelines, memory management, and lifecycle observability
• Define RAG pipeline standards, chunking/embedding strategies, quality benchmarks, and transferable metrics
• Set multi-LLM integration standards and cost-governance across providers (OpenAI, Anthropic, Vertex AI, open-source models)
• Own LLMOps at programme scale: eval strategies, prompt governance, observability tooling, safety monitoring, and cost controls
• Lead client engineering engagements at senior level: design sessions, proof-of-concept delivery, and alignment between client leadership and delivery teams




• Publish reusable patterns, accelerators, and engineering standards for scalable adoption across engagements
• Own the measurement framework for agentic system quality (accuracy, latency, safety, cost); present AI impact to senior stakeholders
Responsabilidades
• Software engineering in production environments
• Hands-on experience delivering production agentic AI solutions
• Experience with agentic orchestration frameworks (LangGraph, CrewAI, AutoGen) at production depth
• Direct experience calling LLM APIs in production code (OpenAI, Anthropic, Vertex AI)
• RAG pipeline ownership (embeddings, chunking, vector xqbhyrx databases, context engineering)
• LLMOps fundamentals (eval harness, prompt versioning, production observability)
• Cloud-native engineering maturity (Kubernetes, Docker, microservices, serverless, CI/CD, IaC)
• Strong Python; Java or equivalent backend language; production debugging and observability
• Leadership experience managing and developing a team of engineers
Requisitos principales
• vendor fellowship access inside Anthropic, OpenAI, Microsoft, and Google engineering teams
• Forward Deployed Engineer programme
• certifications and learning opportunities
• global exposure across industries

📌 AI Native Engineer (Agentic / Applied) (Madrid)
🏢 Accenture
📍 Madrid