Overview In this role you design, build, and deploy production-grade agentic AI systems across the enterprise stack, collaborating directly with client engineering teams. You own end-to-end orchestration, RAG pipelines, and multi-provider integration to scale across engagements. You will implement LLMOps, observability, and cost/safety monitoring while developing reusable patterns and accelerators that accelerate future work. This is a hands-on, client-facing opportunity to shape enterprise AI solutions at scale.

ResponsabilidadesDesign and build production-grade agentic systems end-to-end: multi-agent orchestration, RAG pipelines, policy-based routing, tool invocation, memory management, and lifecycle observabilityBuild and own RAG pipelines: embeddings, chunking strategy, vector search, context window engineeringIntegrate and abstract across multiple LLM providers — OpenAI, Anthropic, Vertex AI, and open-source models — with fallback routing, token, cost, and latency managementImplement LLMOps in production: eval harnesses with real quality metrics, prompt versioning, observability tooling (LangSmith, Braintrust, or equivalent), cost and safety monitoringEmbed directly with client engineering teams to design, prototype, and deploy agentic solutions — workshops, proofs of concept, code-with sessions, and architecture walkthroughsBuild reusable patterns, accelerators, and playbooks that scale beyond the individual client engagement and enable the next one to start fasterDefine and use metrics to measure agent accuracy, latency, safety,



and cost-effectiveness; present findings and recommendations to client stakeholders in business terms Requisitos principalesStrong software engineering experience in production environmentsHands-on experience designing and deploying agentic AI solutions in a production environmentDemonstrated experience with agentic orchestration frameworks: LangGraph, CrewAI, AutoGen, or equivalentDirect experience calling LLM APIs (OpenAI, Anthropic, Vertex AI) in production code: provider abstraction, token management, latency and cost tradeoffsRAG pipeline ownership: embeddings, chunking strategy, vector databases, and context engineeringLLMOps fundamentals: eval harness design, prompt versioning, and production observabilityCloud-native engineering maturity: Kubernetes, Docker, microservices, serverless, CI/CD, and IaC (Terraform or Helm)Strong Python; Java or equivalent backend language acceptable; production debugging and observability experienceQuality of experience is weighted over years, a candidate who has shipped three production agentic systems in four years is preferred over a generalist with passive AI exposureLangGraph, CrewAI, AutoGen or equivalent agentic orchestration frameworksLLM APIs (OpenAI, Anthropic, Vertex AI) in productionRAG pipelines: embeddings, chunking, vector databases, context engineeringLLMOps: eval harnesses, prompt versioning, production observabilityKubernetes, Docker, microservices, serverless, CI/CD, IaC (Terraform or Helm)Python; Java or equivalent backend language

📌 AI Software Engineer | Spain (Barcelona)
🏢 Jobrapido
📍 Barcelona