Agentic AI Engineer - Production Systems Builder

Accenture France; Paris; Sur place; EUR 90 000 - 130 000; Plein temps

Résumé du poste

Accenture France is seeking an AI Engineer (Agentic/Applied) to design, build, and deploy production-grade agentic AI systems across the enterprise tech stack. You will collaborate with client engineering teams, lead design sessions, and create scalable patterns and accelerators for future engagements.

This role emphasizes hands-on production work, eval harnesses, and observability, with direct exposure to leading LLM providers and cloud-native architectures.

Qualifications

• Three production agentic AI systems shipped in four years.
• Minimum 2–5 years software engineering in production environments.
• Experience with agentic orchestration frameworks at production depth.
• Direct experience calling LLM APIs (OpenAI, Anthropic, Vertex AI) in production code.

Responsabilités

• Design and build production-grade agentic systems end-to-end.
• Own RAG pipelines: embeddings, chunking, vector search.
• Integrate across LLM providers with routing, cost, and latency management.
• Implement LLMOps in production: eval harnesses, prompt versioning, observability.
• Work with client engineering teams through workshops, PoCs, and architecture walkthroughs.
• Build reusable patterns and accelerators for future engagements.
• Define metrics for agent accuracy, latency, security, and cost; present business insights.

Connaissances

Agentic AI

Production systems

RAG pipelines

LLMOps

LangGraph

CrewAI

AutoGen

OpenAI

Vertex AI

Kubernetes

Docker

CI/CD

Terraform

Helm

Python

Java

Outils

LangSmith

Braintrust

Description du poste

Accenture France is seeking an AI Engineer (Agentic/Applied) to design, build, and deploy production-grade agentic AI systems across the enterprise tech stack. You will collaborate with client engineering teams, lead design sessions, and create scalable patterns and accelerators for future engagements.

This role emphasizes hands-on production work, eval harnesses, and observability, with direct exposure to leading LLM providers and cloud-native architectures.