AI Software Engineer
hace 4 horas
Madrid
ppbWe are: /b /p pA forward-thinking services company at the forefront of AI-native innovation. We partner with enterprise clients to create next-generation, agent-powered workflows engineered to scale in real-world settings. Our engineers embed deeply with customers, moving projects beyond experimentation into operational reality. /p pbYou are /b /p pAn AI Native Engineer with a strong foundation in building cloud-native solutions and hands-on experience designing and deploying agentic systems, especially for enterprise environments. You’re a critical thinker who thrives in ambiguity, delivering concrete results by designing, building, and running AI agents that augment workflows and scale across modern infrastructure. /p pYou'll shape how enterprises adopt AI-native engineering - either by leading complex agentic solutions and developing engineering talent, or by owning critical technical areas end-to-end as a senior IC /p pbThe Work /b /p pYou’ll partner directly with client stakeholders — acting as both technologist and trusted advisor. You’ll partner with stakeholders to define use cases, rapidly prototype, and deploy agentic workflows that are robust, secure, and operational in complex enterprise domains. Often, these will be net-new platforms and systems that need to be stitched together in our clients’ environments alongside our ecosystem partners. /p pbAgent Architecture Engineering /b /p ul lipDesign and build enterprise-ready AI agents incorporating retrieval, orchestration, policy-based routing, tool invocation, evaluation harnesses, and lifecycle observability. /p /li lipImplement resilient, testable, and maintainable agentic workflows that can be iterated on quickly. /p /li /ul pbAI Platform Integration /b /p ul lipDevelop and/or extend abstraction layers across AI providers (Anthropic, Google, OpenAI, etc.) to enable seamless integration and multi-provider enablement. /p /li lipContribute to shared libraries, SDKs, and patterns that can be reused across clients. /p /li /ul pbCloud-Native Engineering /b /p ul lipLeverage containerization (Kubernetes, Docker), microservices, serverless, event-driven architectures, CI/CD, and observability stacks to deliver scalable AI-native systems. /p /li lipOwn deployment, monitoring, and troubleshooting for your services in production. /p /li /ul pbDomain-Specific Workflows /b /p ul lipTailor and deploy agentic applications across verticals (e.g., finance, healthcare, retail), adapting to domain-specific processes and constraints. /p /li lipWork closely with client SMEs to translate business workflows into agentic solutions. /p /li /ul pbClient Engagement /b /p ul lipParticipate in and/or lead design workshops, POCs, and code-with sessions to shape data-driven agent workflows with stakeholders, fostering trust and adoption. /p /li lipCommunicate trade-offs, risks, and recommendations clearly to both technical and non-technical audiences. /p /li /ul pbMeasure Improve /b /p ul lipDefine and use key metrics, test harnesses, and evaluation plans to measure agent accuracy, latency, safety, and cost effectiveness. /p /li lipIterate rapidly based on data, feedback, and changing requirements. /p /li /ul pbKnowledge Sharing /b /p ul lipCraft reusable patterns, documentation, and best practices that influence internal assets and client roadmaps. /p /li lipContribute to internal communities of practice around AI-native and agentic engineering. /p /li /ul pTravel may be required for this role. The amount of travel will vary from 25% to 75% depending on business need and client requirements. /p h3Key Responsibilities /h3 ul lipUse AI coding assistants daily as a standard part of delivery, actively, frequently, and with demonstrable impact on productivity and output quality /p /li lipIntegrate LLM APIs into applications in production: calling AI provider APIs in live code, managing token limits and latency, and building initial abstraction layers /p /li lipApply AI across the full software delivery lifecycle: AI-generated tests, AI-assisted debugging, AI-accelerated code review, and prompt engineering for development tasks /p /li lipOwn the quality of AI-generated outputs in your delivery scope, exercise engineering judgment about reliability, limitations, and failure modes; know when AI output is production-ready and when it is not /p /li lipDefine and track KPIs to evaluate the effectiveness and ROI of AI-assisted workflows; present AI productivity and quality metrics to project stakeholders /p /li lipOwn delivery end-to-end — from design through to production support — in Agile sprint cycles alongside client engineering teams /p /li lipContribute to shared knowledge bases, reusable components, and internal AI tooling standards that benefit the wider team /p /li lipBuild and integrate the application layers, APIs, and interfaces that connect full-stack systems to agentic backends — understanding data flows, context handoffs, and integration points between your code and AI pipelines /p /li /ul h3Basic Qualifications /h3 ul lipBachelor's degree in Computer Science, Computer Engineering, Software Engineering, or a related field /p /li lipComercial software engineering experience in production environments (or equivalent demonstrated through academic projects, internships, or shipped personal projects) /p /li lipProficiency in at least one primary backend language: Python, Java, or TypeScript /p /li lipDemonstrated hands-on experience using AI tools actively in day-to-day engineering work — with practical examples of how AI was used to solve real problems, iterate on outputs, and improve delivery; including direct experience calling LLM APIs in production code with an understanding of token management, latency, and cost tradeoffs /p /li lipBasic understanding of web technologies including JavaScript, HTML, and CSS /p /li lipFamiliarity with cloud fundamentals (AWS, Azure, or GCP), containers (Docker), and CI/CD pipelines /p /li lipUnderstanding of Agile delivery fundamentals /p /li lipExperience with databases — SQL or NoSQL /p /li lipAbility to validate, evaluate, and improve AI-generated outputs; understanding of AI limitations and responsible use /p /li lipFamiliarity with agentic system concepts — awareness of orchestration frameworks (LangChain, LangGraph, or equivalent), RAG pipelines, and how full-stack applications connect to agent-based architecture; production experience preferred, conceptual understanding required /p /li /ul pbWe are: /b /p pA forward-thinking services company at the forefront of AI-native innovation. We partner with enterprise clients to create next-generation, agent-powered workflows engineered to scale in real-world settings. Our engineers embed deeply with customers, moving projects beyond experimentation into operational reality. /p pbYou are /b /p pAn AI Native Engineer with a strong foundation in building cloud-native solutions and hands-on experience designing and deploying agentic systems, especially for enterprise environments. You’re a critical thinker who thrives in ambiguity, delivering concrete results by designing, building, and running AI agents that augment workflows and scale across modern infrastructure. /p pYou'll shape how enterprises adopt AI-native engineering - either by leading complex agentic solutions and developing engineering talent, or by owning critical technical areas end-to-end as a senior IC /p pbThe Work /b /p pYou’ll partner directly with client stakeholders — acting as both technologist and trusted advisor. You’ll partner with stakeholders to define use cases, rapidly prototype, and deploy agentic workflows that are robust, secure, and operational in complex enterprise domains. Often, these will be net-new platforms and systems that need to be stitched together in our clients’ environments alongside our ecosystem partners. /p pbAgent Architecture Engineering /b /p ul lipDesign and build enterprise-ready AI agents incorporating retrieval, orchestration, policy-based routing, tool invocation, evaluation harnesses, and lifecycle observability. /p /li lipImplement resilient, testable, and maintainable agentic workflows that can be iterated on quickly. /p /li /ul pbAI Platform Integration /b /p ul lipDevelop and/or extend abstraction layers across AI providers (Anthropic, Google, OpenAI, etc.) to enable seamless integration and multi-provider enablement. /p /li lipContribute to shared libraries, SDKs, and patterns that can be reused across clients. /p /li /ul pbCloud-Native Engineering /b /p ul lipLeverage containerization (Kubernetes, Docker), microservices, serverless, event-driven architectures, CI/CD, and observability stacks to deliver scalable AI-native systems. /p /li lipOwn deployment, monitoring, and troubleshooting for your services in production. /p /li /ul pbDomain-Specific Workflows /b /p ul lipTailor and deploy agentic applications across verticals (e.g., finance, healthcare, retail), adapting to domain-specific processes and constraints. /p /li lipWork closely with client SMEs to translate business workflows into agentic solutions. /p /li /ul pbClient Engagement /b /p ul lipParticipate in and/or lead design workshops, POCs, and code-with sessions to shape data-driven agent workflows with stakeholders, fostering trust and adoption. /p /li lipCommunicate trade-offs, risks, and recommendations clearly to both technical and non-technical audiences. /p /li /ul pbMeasure Improve /b /p ul lipDefine and use key metrics, test harnesses, and evaluation plans to measure agent accuracy, latency, safety, and cost effectiveness. /p /li lipIterate rapidly based on data, feedback, and changing requirements. /p /li /ul pbKnowledge Sharing /b /p ul lipCraft reusable patterns, documentation, and best practices that influence internal assets and client roadmaps. /p /li lipContribute to internal communities of practice around AI-native and agentic engineering. /p /li /ul pTravel may be required for this role. The amount of travel will vary from 25% to 75% depending on business need and client requirements. /p /p #J-18808-Ljbffr