3 days ago
Saint-Herblain, FranceStaff+
Responsibilities
- Architect and govern production-grade agentic systems, including multi-agent orchestration, RAG pipelines, policy-based routing, memory management, and lifecycle observability.
- Define RAG standards covering chunking, embeddings, quality benchmarks, and documented tradeoffs.
- Set vendor-agnostic multi-LLM integration standards, including fallback routing, token management, latency, and cost governance.
- Own programme-level LLMOps, including evaluation strategy, prompt governance, observability, safety monitoring, and cost controls.
- Lead client architecture sessions, proof-of-concept delivery, and alignment between technology leadership and delivery teams.
- Create reusable engineering patterns, accelerators, and standards for future client engagements.
- Define and communicate agentic-system quality metrics covering accuracy, latency, safety, and cost.
- Manage, develop, and performance-manage engineers, including development planning and career conversations.
Requirements
- Significant production software engineering experience is required.
- Hands-on production experience designing and deploying agentic AI solutions is required.
- Production-depth experience with LangGraph, CrewAI, AutoGen, or an equivalent agentic orchestration framework is required.
- Production experience using OpenAI, Anthropic, or Vertex AI APIs, including provider abstraction, token management, and latency and cost tradeoffs, is required.
- Experience owning RAG pipelines, embeddings, chunking strategies, vector databases, and context engineering is required.
- Experience designing evaluation harnesses, versioning prompts, and operating production observability is required.
- Cloud-native experience with Kubernetes, Docker, microservices, serverless systems, CI/CD, and infrastructure as code using Terraform or Helm is required.
- Strong Python skills are required; Java or an equivalent backend language is acceptable.
- Production debugging and observability experience is required.
- Candidates who have shipped three production agentic systems in four years are preferred over candidates with passive AI exposure.
- Experience managing, developing, and performance-managing engineering teams is required.
Tech Stack
Categories
About Accenture
Accenture is a global professional services firm providing management consulting, systems integration and technology, cybersecurity, and business process outsourcing for enterprises and governments. It operates a services-driven model delivering projects and managed services, often with major cloud and software partners, across industries worldwide. Headquartered in Dublin and publicly traded on the NYSE (ACN), it originated as Andersen Consulting and adopted the Accenture name in 2001.