> Markdown version of [/jobs/ext/4777013-ai-agent-developer](https://www.wearedevelopers.com/jobs/ext/4777013-ai-agent-developer). 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 Agent Developer - **Company:** Novanta Inc. - **Location:** Barcelona, Spain - **Contract:** Permanent contract - **Skills:** Application Programming Interfaces (APIs), Artificial Intelligence, Amazon Web Services, Cloud Engineering, Continuous Integration, Data Stores, DevOps, Radio-Frequency Identification, Performance Tuning, Software Engineering, Management of Software Versions, Cloud Platform System, Evaluation Pipelines, Retrieval-Augmented Generation, Generative AI, Backend, Build Management, AI Platforms, Kubernetes, Infrastructure Automation Frameworks, Information Technology, Operational Systems, Claude, Virtual Agents - **Published:** November 19, 2026 - **Apply:** https://novanta.wd5.myworkdayjobs.com/Novanta-Careers/job/Barcelona-Spain---Keonn/AI-Agent-Developer_R009902 ## About the Role * Bachelor's or Master's degree in Computer Science, Software Engineering, AI/ML, or a related field. * 4+ years of software engineering experience, with hands-on backend and cloud development. * Overview of building GenAI or LLM-based applications in production or near-production environments. * Understanding of agentic patterns: tool use, retrieval (RAG), planning/execution loops, and memory/context design. * Experience integrating model APIs and orchestration frameworks. * Solid software engineering fundamentals: testing, versioning, observability, reliability, and performance optimization. * Familiarity with evaluation methods, safety controls, and responsible AI practices. * Strong collaboration and communication skills in cross-functional teams. * Fluent in English; Catalan or Spanish is a plus. * Resident of the EU or eligible to work in Spain (permanent residence in Spain) Nice-to-have (we prefer) * Experience with MCP-compatible architectures and enterprise tool ecosystems. * Experience with Claude, Bedrock, or comparable model platforms. * Experience with AWS and modern DevOps practices (CI/CD, monitoring, infrastructure automation). * Background in retail tech, RFID, IoT, or real-time operational systems. * Experience designing human-in-the-loop workflows and escalation mechanisms. * Exposure to security and compliance frameworks relevant to enterprise SaaS. ## Description We are looking for an outstanding AI Agent Engineer to join the shopOS initiative within Keonn's Cloud Platform organization. ShopOS is our strategic initiative to bring practical AI into retail operations. Our goal is to transform real-time store data into intelligent actions that improve inventory accuracy, operational execution, and decision-making quality at scale. In this role, you will design and build production-grade AI agents and the platform capabilities around them: runtime orchestration, tool integrations, context/memory handling, evaluation pipelines, and safety controls. You will work closely with platform, product, and domain teams to move from pilot use cases to reliable, measurable, real-world impact. This role is ideal for engineers who enjoy combining software engineering rigor with applied GenAI innovation. Your Responsibilities * Build core agent capabilities, including runtime orchestration, tools, connectors, context, and memory. * Implement access patterns to internal/external APIs and intelligence services (including MCP-style integrations where relevant). * Develop robust agent-tool interaction layers for analytics, operational workflows, and platform services. * Create and maintain evaluation frameworks for agent quality, reliability, and business usefulness. * Define and implement guardrails: permissions, traceability, auditability, and human-in-the-loop oversight. * Measure and optimize key performance indicators such as usefulness, accuracy, latency, cost, and incident rate. * Collaborate with Cloud Platform teams to ensure secure, scalable, and observable deployment in AWS environments. * Work with Product and domain experts to convert business opportunities into prioritized, testable AI capabilities. * Contribute to engineering standards, documentation, and operational readiness for AI services in production.