AI Native Software Engineer, Madrid
Sin Especificar
Accenture
Madrid, Madrid,
hace 3 días
... based routing, tool invocation, memory management, and lifecycle observability - Build and ... , token, cost, and latency management - Implement LLMOps in production: eval ... code: provider abstraction, token management, latency and cost tradeoffs - RAG ...
www.tecnoempleo.com