Overview

In this role you design, build, and deploy production-grade agentic AI systems across enterprise stacks, working directly with client engineering teams. You’ll lead technical design, publish reusable patterns, and ensure scalable, observable AI solutions that run in client environments. You shape the tooling and governance around RAG pipelines, multi-LLM integration, and LLMOps across programs. This is a hands-on position with significant client impact and opportunities to collaborate with leading AI engineering teams.

Retribuzione / Benefits

- vendor fellowship access inside Anthropic, OpenAI, Microsoft and Google engineering teams
- Forward Deployed Engineer programme
- broad cross-industry exposure
- career development opportunities
- global delivery capability
- competitive compensation depending on role and seniority

Responsabilità

- Architect and govern production-grade agentic systems at enterprise scale including multi-agent orchestration, RAG pipelines, memory management, and lifecycle observability
- Define RAG pipeline standards: chunking, embeddings, quality benchmarks, measurable trade-offs
- Set multi-LLM integration standards with vendor-agnostic design and cost governance
- Own LLMOps at program scale: eval strategy, prompt governance, observability, safety, and cost controls
- Lead client engineering engagements at senior level: design sessions, POC delivery, align client leadership with delivery
- Shape and publish reusable patterns, accelerators, and standards to scale engagements
- Own the measurement framework for agentic system quality: define metrics and present AI impact to senior stakeholders




- Demonstrate production software engineering experience and hands-on deployment of agentic AI solutions
- Demonstrated experience with agentic orchestration frameworks in production (LangGraph, CrewAI, AutoGen, or equivalent)
- Direct experience calling LLM APIs (OpenAI, Anthropic, Vertex AI) in production and managing latency/cost tradeoffs
- RAG pipeline ownership: embeddings, chunking, vector databases, context engineering
- LLMOps fundamentals: eval harness design, prompt versioning, production observability
- Cloud-native maturity: Kubernetes, Docker, microservices, CI/CD, IaC (Terraform or Helm)
- Strong Python; Java or equivalent backend language; production debugging and observability
- Experience leading teams of engineers and mentoring talent
- Ability to ship three production agentic systems in four years is preferred over broad AI exposure

Requisiti fondamentali

- production-level software engineering experience
- hands-on experience deploying agentic AI solutions in production
- experience with agentic orchestration frameworks (LangGraph, CrewAI, AutoGen, or equivalent) in production
- experience calling LLM APIs (OpenAI, Anthropic, Vertex AI) in production
- RAG pipeline ownership (embeddings, chunking, vector databases)
- LLMOps fundamentals (eval harness, prompt versioning, observability)
- cloud-native engineering (Kubernetes, Docker, microservices, CI/CD, IaC)
- strong Python; Java or equivalent backend language
- people leadership: managing and developing a team of engineers

- leadership
- client-facing communication
- architecture design facilitation
- LangGraph
- CrewAI
- AutoGen

📌 AI Native Associate Director (Salerno)
🏢 Accenture
📍 Salerno