AI Software Engineer (Agentic AI)

About the role

Accenture is hiring an AI Software Engineer in Madrid to build production-grade agentic AI systems used in real enterprise environments, not prototypes. You will design, build and deploy agentic systems across the full enterprise technology stack, work directly with client engineering teams, lead technical design sessions and build reusable patterns and accelerators that scale beyond individual engagements.

Key responsibilities

• Design and build production-grade agentic systems end-to-end: multi-agent orchestration, RAG pipelines, policy-based routing, tool invocation, memory management and lifecycle observability.
• Build and own RAG pipelines: embeddings, chunking strategy, vector search and context window engineering tuned to real quality targets.
• Integrate and abstract across multiple LLM providers (OpenAI, Anthropic, Vertex AI and open-source models) with fallback routing and token, cost and latency management.
• Implement LLMOps in production: eval harnesses with real quality metrics, prompt versioning and observability tooling such as LangSmith or Braintrust, plus cost and safety monitoring.
• Work with client engineering teams on workshops, proofs of concept, code-with sessions and architecture walkthroughs.
• Build reusable patterns, accelerators and playbooks that speed up future engagements.
• Measure agent accuracy, latency, safety and cost-effectiveness and present findings to client stakeholders in business terms.

Required profile

• Strong software engineering experience in production environments.
• Hands-on experience designing and deploying agentic AI solutions in production (non-negotiable).
• Demonstrated experience with agentic orchestration frameworks such as LangGraph, CrewAI or AutoGen at production depth.
• Experience calling LLM APIs in production code and owning RAG pipelines.
• LLMOps fundamentals: eval harness design, prompt versioning and production observability.
• Cloud-native engineering maturity: Kubernetes, Docker, microservices, serverless, CI/CD and IaC (Terraform or Helm).
• Strong Python; Java or an equivalent backend language is acceptable.
• Quality of experience is weighted over years; having shipped three production agentic systems in four years is preferred.