Senior Production Agentic AI Architect

3500 Accenture S.A.S. Company; Paris; Sur place; EUR 110 000 - 170 000; Plein temps

Résumé du poste

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

You will own LLMOps, define RAG pipelines, and establish multi-LLM integration standards across providers. Strong Python and backend skills are essential.

Qualifications

• 8+ years of software engineering in production environments.
• Hands-on experience designing and deploying agentic AI solutions in production.
• Direct experience calling LLM APIs (OpenAI, Anthropic, Vertex AI) in production code.
• Experience with agentic orchestration frameworks at production depth.

Responsabilités

• Architect and govern production-grade agentic systems at enterprise scale across multi-agent environments.
• Define RAG pipeline standards and embedding strategies with measurable quality.
• Set multi-LLM integration standards across providers including OpenAI and Vertex AI.
• Own LLMOps strategy: eval, prompts governance, observability, and cost controls.
• Lead client engagements, drive architecture sessions, and deliver poof-of-concept work.
• Publish reusable patterns and accelerators to scale practices across engagements.
• Own measurement framework for agentic system quality and business impact.

Connaissances

Agentic AI

LLMOps

RAG pipelines

Kubernetes

Docker

Python

Java

LLM APIs

Production deployment

Observability

LangGraph

CrewAI

AutoGen

Outils

LangGraph

CrewAI

AutoGen

OpenAI API

Vertex AI

Description du poste

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

You will own LLMOps, define RAG pipelines, and establish multi-LLM integration standards across providers. Strong Python and backend skills are essential.