ph3Responsibilities /h3 ul liWe are looking for a Staff AI Engineer to play a key role in building the core of our AI platform /li liIn this position, you will design and develop production-grade systems that power intelligent automation, agentic workflows, and large-scale retrieval services /li liThis is a highly technical, hands‑on role that involves close collaboration with product and platform teams to transform advanced AI concepts into reliable, scalable, and secure solutions used across our enterprise ecosystem /li liDesign, build, and maintain AI-powered services and APIs, leveraging LLMs (OpenAI, Anthropic, Qwen, OSS models) and custom ML models /li liDevelop an enterprise‑grade agentic framework that enables orchestration, retrieval, and collaboration between multiple AI agents /li liImplement and optimise knowledge retrieval systems and agentic search capabilities using vector databases such as Qdrant and ElasticSearch /li liWrite well‑structured, efficient, and testable Python code for production services, experimentation, and internal developer tools /li liBuild and maintain shared Python libraries and SDKs used across multiple applications and microservices /li liCollaborate with cross‑functional teams on architecture, internal protocols, and API standards to ensure consistency and reliability across the platform /li liDevelop and enhance monitoring, validation, and observability for production‑grade AI solutions /li liDrive the full software development lifecycle – from design and implementation to deployment, monitoring, and continuous improvement /li liIdentify and resolve performance bottlenecks, reliability issues, and scaling challenges in complex, data‑intensive environments /li liParticipate in code reviews and technical discussions,



mentoring other engineers and contributing to a culture of excellence /li liExample Projects – Building an evaluation and observability framework for AI model performance and reliability /li liExample Projects – Developing an agentic orchestration platform that enables collaboration among multiple AI agents and tools /li liExample Projects – Implementing semantic retrieval and agentic search capabilities over large enterprise knowledge bases /li liExample Projects – Designing AI services that process and reason over high‑volume real‑world data at scale /li /ul h3Benefits /h3 ul liFlexible Working Arrangements: We maintain a hybrid remote work model and provide everyone with best of breed technology tools that enable them to work anywhere, anytime. /li liGreat Employee Benefits: Such as an Employee Assistance Programme (EAP), Health Insurance, Referral Bonuses, and Workato Stock Options, tailored to the countries that our employees are based in. /li liProfessional Development Opportunities: We support individual career ambitions, and set aside training programs and budgets they can tap on to upgrade both soft and hard skills. /li liRecreation Time: From virtual game nights to fitness sessions, there’s always time for a little fun on the calendars. /li liDedicated Wellness: We make it a point to dedicate time to pause, recharge and get to know each other better. /li /ul h3Qualifications /h3 ul li5+ years of experience as a Software Engineer,



with strong proficiency in Python /li liKnowledge of DevOps and observability practices (CI/CD, monitoring, metrics, and model validation) /li liExperience with relational and non‑relational databases (PostgreSQL, Elastic, Qdrant, or similar) /li liFamiliarity with AI/ML system design, including LLM integration and evaluation pipelines /li liStrong understanding of distributed systems, API design, and data‑driven architectures /li liProven track record of building and maintaining production‑grade systems using Python /li liBachelor’s or Master’s degree in Computer Science, Engineering, or a related field, or equivalent practical experience /li liProficiency with Python, FastAPI, LLM APIs (OpenAI, Anthropic, Qwen, OSS), LiteLLM, Qdrant, PostgreSQL, ElasticSearch, Langfuse, Kubernetes, GitHub Actions, ArgoCD /li liExperience working with multiple LLM providers (OpenAI, Anthropic, Qwen, open‑source models) /li liBackground in developer platforms or AI infrastructure services /li liExposure to Langfuse, LiteLLM, LangChain, or similar frameworks /li liFamiliarity with vector databases, semantic retrieval, and knowledge graph architectures /li liExperience developing enterprise‑scale SaaS or distributed backend systems /li liContributions to open‑source projects in Python, AI, or infrastructure engineering /li liStrong analytical and problem‑solving abilities, with a focus on continuous improvement and innovation /li liExcellent communication skills, with the ability to convey complex technical ideas clearly to both technical and non‑technical audiences /li liCuriosity and a genuine interest in emerging AI technologies and modern backend architectures /li liCollaborative and proactive approach, comfortable working across teams in a dynamic environment /li /ul /p #J-18808-Ljbffr

📌 Staff AI Engineer (Madrid)
🏢 Workato
📍 Madrid