Overview

In this role you build production-grade agentic AI systems that scale across enterprise environments. You’ll work directly with client engineering teams to design, deploy, and govern multi-agent architectures and reusable patterns. The position sits at the core of Accenture’s AI practice, offering breadth across industries and direct access to leading engineering ecosystems. You’ll tackle real-world reliability, latency, and cost tradeoffs, shaping impactful AI deployments. This is an opportunity to lead the design and delivery of mission-critical AI systems at scale.

Compensaciones / Ventajas

- vendor fellowship access inside leading AI companies
- Forward Deployed Engineer programme
- broad industry exposure
- career development opportunities
- global delivery capability

Responsabilidades

- Architect and govern production-grade agentic systems at enterprise scale, including multi-agent orchestration, RAG pipelines, policy routing, memory management, and observability
- Define RAG pipeline standards: chunking, embeddings, quality benchmarks, and metric-backed decisions
- Set multi-LLM integration standards with vendor-agnostic architecture and cost governance across providers
- Own LLMOps at programme scale: eval strategy, prompt governance, observability, safety monitoring, and cost controls
- Lead client engineering engagements at senior level: architecture sessions, PoC delivery,



aligning client leadership and delivery
- Shape and publish reusable patterns, accelerators, and engineering standards for scalable engagement ramps
- Own measurement framework for agentic system quality: metrics for AI impact and business value to stakeholders

Requisitos principales

- Software engineering experience in production environments
- Hands-on production experience with agentic AI solutions
- Experience with agentic orchestration frameworks at production depth (e.g., LangGraph, CrewAI, AutoGen)
- Direct production experience calling LLM APIs (OpenAI, Anthropic, Vertex AI) with provider abstraction, token management, latency and cost tradeoffs
- 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 (Terraform or Helm)
- Strong Python; Java or equivalent backend language; production debugging and observability
- People leadership: managing and developing a team of engineers; performance management
- Track record of shipping three production agentic systems in four years preferred

- leadership
- communication with client stakeholders
- architecture facilitation
- LangGraph
- CrewAI
- AutoGen

📌 Forward Deployed Engineer (Sevilla)
🏢 Accenture
📍 Sevilla