Production AI Engineer: Agentic Systems Architect

Accenture PLC; Dublin; On-site; EUR 90,000 - 130,000; Full time

Job summary

Accenture PLC is seeking an AI Engineer (Agentic/Applied) to design, build, and deploy production-grade agentic AI systems across the enterprise tech stack. You will work directly with client engineering teams, lead technical design sessions, and create reusable patterns that scale beyond individual engagements.

The role requires hands-on experience shipping multi-agent systems in production, owning eval harnesses, and readiness to manage 2am incidents.

Qualifications

• Software engineering in production environments required.
• Minimum 1 year designing and deploying agentic AI solutions in production.
• Experience with agentic orchestration frameworks at production depth.
• Direct experience calling LLM APIs (OpenAI, Anthropic, Vertex AI) in production code.
• RAG pipelines ownership and context engineering.
• LLMOps fundamentals: eval harness design and prompt versioning.
• Cloud-native engineering: Kubernetes, Docker, CI/CD, IaC.

Responsibilities

• Design and build production-grade agentic systems end-to-end.
• Build and own RAG pipelines with embeddings and vector search.
• Integrate across LLM providers with routing, token, cost, latency management.
• Implement LLMOps in production with eval harnesses and observability.
• Collaborate with client teams on workshops, PoCs, and architecture walkthroughs.
• Develop reusable patterns and playbooks for future engagements.
• Define metrics for agent accuracy, latency, safety, and cost-effectiveness.

Skills

Python

Java

Backend development

Kubernetes

Docker

LLMOps

Agentic AI

Observability

Production debugging

Cost & latency management

Tools

LangGraph

CrewAI

AutoGen

Job description

Accenture PLC is seeking an AI Engineer (Agentic/Applied) to design, build, and deploy production-grade agentic AI systems across the enterprise tech stack. You will work directly with client engineering teams, lead technical design sessions, and create reusable patterns that scale beyond individual engagements.

The role requires hands-on experience shipping multi-agent systems in production, owning eval harnesses, and readiness to manage 2am incidents.