Production AI Architect: Lead Multi-Agent Systems

Freelio; Denmark; On-site; DKK 800,000 - 1,100,000; Full time

Job summary

Accenture is building production-grade agentic AI systems for enterprise environments, delivering scalable multi-agent architectures and robust LLMOps. The role focuses on design sessions with client teams, publishing reusable patterns, and leading proof-of-concept deliveries across engagements.

You will own evaluation frameworks, prompt governance, and observability, while working with leading AI providers and open-source models to ensure safe, cost-effective, and scalable deployments.

Responsibilities

• Architect and govern production-grade agentic systems at enterprise scale across complex environments and RAG pipelines.
• Define RAG pipeline standards across engagements: chunking, embedding strategies, quality benchmarks, and transferability.
• Set multi-LLM integration standards: vendor-agnostic architecture with fallback routing and cost governance.
• Own LLMOps at programme scale: eval strategy, prompt governance, observability, and cost controls.
• Lead client engineering engagements at senior level: architecture design sessions, proof-of-concept delivery, aligning client tech leadership.
• Shape and publish reusable patterns, accelerators, and engineering standards for faster ramp-up.
• Own the measurement framework for agentic system quality: accuracy, latency, safety, and business impact reporting.
• Direct experience calling LLM APIs (OpenAI, Anthropic, Vertex AI) in production code with provider abstraction.
• RAG pipeline ownership: embeddings, chunking, vector databases, context engineering.
• LLMOps fundamentals: eval harness design, 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.
• Production experience shipping three agentic systems in four years preferred.

Job description

Accenture is building production-grade agentic AI systems for enterprise environments, delivering scalable multi-agent architectures and robust LLMOps. The role focuses on design sessions with client teams, publishing reusable patterns, and leading proof-of-concept deliveries across engagements.

You will own evaluation frameworks, prompt governance, and observability, while working with leading AI providers and open-source models to ensure safe, cost-effective, and scalable deployments.