AI Native Software Engineering Specialist

2 giorni fa

Latina, Lazio, Italia Accenture Tempo pieno

Overview

In this role you design, build, and deploy production-grade agentic AI systems across enterprise tech stacks. You work directly with client engineering teams to craft scalable patterns and accelerators that extend beyond single engagements. The position sits at the core of delivering production AI, with exposure to top tech ecosystems and fellowship programs. You will shape how multi-agent systems operate in real client environments, from architecture to observability.

Responsabilità

  • Design and build end-to-end production-grade agentic systems (multi-agent orchestration, RAG pipelines, policy routing, tool invocation, memory management, observability)
  • Own RAG pipelines (embeddings, chunking, vector search, context window tuning)
  • Integrate across multiple LLM providers (OpenAI, Anthropic, Vertex AI, open-source models) with fallback routing and cost/latency management
  • Implement LLMOps in production (eval harnesses, prompt versioning, observability tooling, cost and safety monitoring)
  • Collaborate with client teams to design, prototype, and deploy agentic solutions (workshops, proofs of concept, code-with sessions)
  • Build reusable patterns, accelerators, and playbooks for scalable engagements
  • Define and use metrics for agent accuracy, latency, safety, and cost-effectiveness; present findings to client stakeholders

Requisiti fondamentali

  • Hands-on experience designing and deploying agentic AI solutions in production
  • Experience with agentic orchestration frameworks (LangGraph, CrewAI, AutoGen) at production depth
  • Direct experience calling LLM APIs (OpenAI, Anthropic, Vertex AI) in production code
  • 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, CI/CD, IaC Terraform or Helm)
  • Strong Python; Java or equivalent backend language; production debugging/observability experience
  • Track record shipping multiple production agentic systems in four years preferred
  • client collaboration
  • problem-solving under pressure
  • clear technical communication
  • LangGraph
  • CrewAI
  • AutoGen