16 ott - Roma
Accenture
OverviewIn this role you will design, build, and deploy production-grade agentic AI systems for enterprise environments, working directly with client teams to scale reusable patterns. You will lead technical design sessions, set standards for RAG pipelines, and own the LLMOps program at scale. The position sits at the core of Accenture’s AI engineering practice, offering exposure to a broad range of industries and close collaboration with top AI teams. You will shape impactful, production-ready solutions that drive business value.
Responsabilità
Architect and govern production-grade agentic systems at enterprise scale (multi-agent orchestration, RAG pipelines, memory management, lifecycle observability)Define RAG pipeline standards across engagements (chunking, embeddings, quality benchmarks)Set multi-LLM integration standards (vendor-agnostic architecture, fallback routing, cost governance)Own LLMOps at programme scale (eval strategy, prompt governance, observability, safety and cost controls)Lead client engineering engagements at senior level (architecture sessions, PoCs, alignment with client leadership)Shape and publish reusable patterns, accelerators, and engineering standardsOwn the measurement framework for agentic system quality (accuracy, latency, safety,
cost metrics)Demonstrable experience with software engineering in production environmentsHands-on experience designing and deploying agentic AI solutions in productionExperience with agentic orchestration frameworks (LangGraph, CrewAI, AutoGen)Direct experience calling LLM APIs (OpenAI, Anthropic, Vertex AI) in productionRAG pipeline ownership (embeddings, chunking, vector DBs, context engineering)LLMOps fundamentals (eval harness design, prompt versioning, observability)Cloud-native engineering maturity (Kubernetes, Docker, microservices, serverless, CI/CD, IaC)Strong Python; Java or equivalent backend language; production debugging and observability
Requisiti fondamentali
Production-grade agentic systems shipped in productionHands-on experience with agentic orchestration frameworks (LangGraph, CrewAI, AutoGen)Production experience calling LLM APIs (OpenAI, Anthropic, Vertex AI)RAG pipelines and vector databases managementLLMOps, prompt governance, evaluation and observabilityCloud-native skills (Kubernetes, Docker, microservices, CI/CD, IaC)Strong backend programming skills (Python; Java or equivalent)People leadership and team development experienceleadershipcustomer-facing communicationarchitecture facilitationLangGraphCrewAIAutoGen
17 ott - Piove di sacco
In Job S. P. A.
17 ott - Roma
elettroteammarrinisrls
17 ott - Piove di sacco
In Job S. P. A.
17 ott - Sestu
OPENJOBMETIS