Overview

Per una comprensione completa di questa occasione e dei requisiti per essere un candidato di successo, continui a leggere.

In this role you design, build, and deploy production-grade agentic AI systems for enterprise environments. You will collaborate with client engineering teams, lead architecture discussions, and create reusable patterns that scale beyond individual engagements. You'll own the end-to-end lifecycle of agentic deployments, from orchestration to observability and cost governance.

This is a hands-on leadership role shaping large-scale AI capabilities across clients, with direct exposure to senior technology leadership.

Responsabilità

- Architect and govern production-grade agentic systems at enterprise scale (multi-agent orchestration, RAG pipelines, memory management, observability)
- Define RAG pipeline standards (chunking, embeddings, quality benchmarks, metrics)
- Set multi-LLM integration standards (vendor-agnostic, routing, cost governance)
- Own LLMOps at programme scale (eval strategy, prompt governance, observability, safety, cost controls)
- Lead client engineering engagements at senior level (architecture design sessions, POC delivery, alignment with leadership)
- Publish reusable patterns, accelerators, and standards for scalable practice




- Own the measurement framework for agentic system quality (accuracy, latency, safety, cost metrics)
- Contribute to production environments with strong software engineering practices

Requisiti fondamentali
- Production-level software engineering experience
- Hands-on agentic AI deployments in production (non-negotiable)
- Experience with agentic orchestration frameworks (LangGraph, CrewAI, AutoGen) at production depth
- Direct experience calling LLM APIs in production (provider abstraction, token management, latency/cost tradeoffs)
- RAG pipeline ownership (embeddings, chunking, vector databases, context xkiyazw engineering)
- LLMOps fundamentals (eval harness, prompt versioning, observability)
- Cloud-native engineering maturity (Kubernetes, Docker, microservices, CI/CD, IaC like Terraform or Helm)
- Strong Python; Java or equivalent backend language; production debugging/observability
- Preferred: track record of shipping three production agentic systems in four years
- People lead responsibilities: managing and developing engineering teams, performance management
- leadership
- stakeholder управдение
- communication
- LangGraph
- CrewAI
- AutoGen

📌 Forward Deployed Engineer (Seconda Municipalità)
🏢 Accenture
📍 Seconda Municipalità