Production AI Agentic Systems Engineer

ALSTOM; Roma; In loco; EUR 32.000 - 54.000; Tempo pieno

Descrizione del lavoro

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

You will own RAG pipelines, integrate multiple LLM providers, and implement robust LLMOps with real metrics and observability, partnering with clients to deliver production-ready AI solutions.

Competenze

• Hands-on experience designing and deploying agentic AI solutions in production.
• Production depth with agentic orchestration frameworks: LangGraph, CrewAI, AutoGen.
• Direct experience calling LLM APIs (OpenAI, Anthropic, Vertex AI) in production.
• RAG pipeline ownership: embeddings, chunking, vector databases, context engineering.
• LLMOps fundamentals: eval harness design, prompt versioning, observability.
• Cloud-native engineering maturity: Kubernetes, Docker, CI/CD, IaC (Terraform or Helm).
• Strong Python; Java or equivalent backend language; production observability.
• Shipped three production agentic systems in four years preferred.

Mansioni

• Design and build production-grade agentic systems end-to-end.
• Build and own RAG pipelines and vector databases.
• Integrate across LLM providers with routing, cost, and latency management.
• Implement LLMOps in production with observability and metrics.
• Work with client engineering teams on workshops and PoCs.
• Create reusable patterns and playbooks for future engagements.
• Measure agent accuracy, latency, safety, and cost; report to stakeholders.

Conoscenze

Agentic AI production

LangGraph

CrewAI

AutoGen

LLMOps

Kubernetes

Docker

CI/CD

Terraform

Helm

Python

Java

Strumenti

LangSmith

Braintrust

Descrizione del lavoro

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

You will own RAG pipelines, integrate multiple LLM providers, and implement robust LLMOps with real metrics and observability, partnering with clients to deliver production-ready AI solutions.