Ai Native Software Engineering Specialist
Pubblicato il 28-09-2026 - Accenture in Provincia di Latina
OverviewScopra di più sui compiti quotidiani, le responsabilità generali e l'esperienza richiesta per questa occasione scorrendo subito verso il basso.In this role you design, build, and deploy production-grade agentic AI systems at scale for enterprise clients. You'll work closely with client engineering teams, lead technical design sessions, and create reusable patterns to accelerate future engagements. The role sits at the intersection of AI engineering and client delivery, with a focus on practical, production-ready solutions. You will influence architecture choices and drive measurable impact across deployments.ResponsabilitàDesign and build end-to-end production-grade agentic systems (multi-agent orchestration, RAG pipelines, policy-based routing, tool invocation, memory management, lifecycle observability)Own RAG pipelines (embeddings, chunking, vector search, context engineering)Integrate across OpenAI, Anthropic, Vertex AI and open-source models with fallback routing and cost/latency managementImplement LLMOps in production (eval harnesses, prompt versioning, observability tooling, cost and safety monitoring)Collaborate with client teams through workshops, proofs of concept, and architecture walkthroughsCreate reusable patterns, accelerators,
and playbooks to scale engagementsDefine and report metrics on agent accuracy, latency, safety, and cost-effectiveness to stakeholdersRequisiti fondamentaliMinimum 1 year designing and deploying agentic AI in productionExperience with agentic orchestration frameworks (LangGraph, CrewAI, AutoGen) at production depthDirect experience calling LLM APIs (OpenAI, Anthropic, Vertex AI) in production codeRAG pipeline ownership (embeddings, chunking, vector databases, context engineering)LLMOps fundamentals (eval harness design, prompt versioning, production observability)Cloud-native xysqume engineering maturity (Kubernetes, Docker, microservices, CI/CD, IaC with Terraform or Helm)Strong Python; Java or equivalent backend language; production debugging and observabilityProduction-shipped experience preferred over generalist exposureclient collaboration and workshop facilitationability to translate technical findings into business termsproblem solving under production pressureagentic orchestration frameworks (LangGraph, CrewAI, AutoGen)LLM APIs (OpenAI, Anthropic, Vertex AI)RAG pipelines and vector databases