> Markdown version of [/jobs/ext/3125762-ai-software-engineer-spain](https://www.wearedevelopers.com/jobs/ext/3125762-ai-software-engineer-spain). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Ai Software Engineer | Spain - **Company:** Accenture - **Location:** Barcelona, Spain - **Contract:** Permanent contract - **Skills:** Java (Programming Language), Application Programming Interfaces (APIs), Artificial Intelligence, Continuous Integration, Software Debugging, Memory Management, Python (Programming Language), Open Source Technology, Search Technologies, Software Engineering, Management of Software Versions, Datadog, Large Language Models, Multi-Agent Systems, Backend, Kubernetes, Low Latency, Production Code, Machine Learning Operations, Virtual Agents, Terraform, Serverless Computing, Docker, Microservices - **Published:** September 28, 2026 - **Apply:** https://www.buscojobs.com.es/ai-software-engineer-spain-en-barcelona-ID-372445600 ## About the Role 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 ## Description OverviewIn 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 termsRequisitos 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 ## Related Videos - [Agentic AI - From Theory to Practice: Developing Multi-Agent AI Systems on Azure](https://www.wearedevelopers.com/videos/1532-agentic-ai-from-theory-to-practice-developing-multi-agent-ai-systems-on-azure) - [Developing the Backend with Stefan Lingler, CTO at Shpock](https://www.wearedevelopers.com/videos/100360-developing-the-backend-with-stefan-lingler-cto-at-shpock) - [Debugging in the Dark](https://www.wearedevelopers.com/videos/1658-debugging-in-the-dark) - [Docker Compose: Rediscovered](https://www.wearedevelopers.com/videos/1978-docker-compose-rediscovered) - [Building a Multi-Agent Orchestration Engine That Actually Follows the Rules](https://www.wearedevelopers.com/videos/100159-building-a-multi-agent-orchestration-engine-that-actually-follows-the-rules) - [Nest.js - TypeScript in the backend can also be clean](https://www.wearedevelopers.com/videos/1033-nest-js-typescript-in-the-backend-can-also-be-clean) ## Related Articles - [How to Become an AI Engineer](https://www.wearedevelopers.com/magazine/331-how-to-become-an-ai-engineer) - [Navigating the AI Shift](https://www.wearedevelopers.com/magazine/629-navigating-the-ai-shift) - [What is Agentic Programming and Why Should Developers Care?](https://www.wearedevelopers.com/magazine/625-what-is-agentic-programming-and-why-should-developers-care) - [MLOps And AI Driven Development](https://www.wearedevelopers.com/magazine/82-mlops-and-ai-driven-development) - [Dev Digest 121 - AI goes offline](https://www.wearedevelopers.com/magazine/456-dev-digest-121-ai-goes-offline) - [Dev Digest 120 - Apple and peers](https://www.wearedevelopers.com/magazine/455-dev-digest-120-apple-and-peers)