AI Manager (Agentic AI Engineer)

About the role

Accenture is hiring an AI Engineer (agentic/applied) in Madrid. You will design, build and deploy production-grade agentic AI systems across the full enterprise technology stack, working directly with client engineering teams, leading technical design sessions and building reusable patterns and accelerators that scale beyond individual engagements.

Key responsibilities

• Architect and govern production-grade agentic systems at enterprise scale: multi-agent orchestration, RAG pipelines, policy-based routing, memory management and programme-level lifecycle observability.
• Define RAG pipeline standards across engagements, including chunking and embedding strategies, quality benchmarks and documented trade-offs.
• Set multi-LLM integration standards with vendor-agnostic architecture, fallback routing and cost governance across providers such as OpenAI, Anthropic, Vertex AI and open-source models.
• Own LLMOps at programme scale: eval strategy, prompt governance, observability tooling standards, safety monitoring and cost controls.
• Lead client engineering engagements at senior level, facilitate architecture design sessions, lead proof-of-concept delivery and align client technology leadership with delivery teams.
• Shape and publish reusable patterns, accelerators and engineering standards, and own the measurement framework for agentic system quality (accuracy, latency, safety, cost).

Required profile

• Strong production software engineering experience; hands-on experience designing and deploying agentic AI solutions in production is non-negotiable.
• Demonstrated experience with agentic orchestration frameworks such as LangGraph, CrewAI or AutoGen at production depth.
• Experience calling LLM APIs (OpenAI, Anthropic, Vertex AI) in production code, with provider abstraction, token management and cost trade-offs.
• Experience owning RAG pipelines: embeddings, chunking strategy, vector databases and context engineering.
• Experience managing, developing and performance-managing a team of engineers, including individual development plans and career conversations.

Required skills

• LLMOps fundamentals: eval harness design, prompt versioning, production observability.
• Cloud-native engineering: Kubernetes, Docker, microservices, serverless, CI/CD and IaC (Terraform or Helm).
• Strong Python; Java or an equivalent backend language is acceptable.