Sr AI Engineer | Remote - Europe | TS/Vue/NodeJS

The AI orchestration of your wildest imagination. n8n is the open workflow orchestration platform built for the new era of AI. ## What you'll bring Ai evaluation ownership: You have hands-on experience building, monitoring, and owning evaluations for production AI or LLM-powered systems. - Post-launch AI improvement: You have monitored shipped AI features, used evaluation signals to identify regressions or failure modes, and improved models, prompts, product flows, or instrumentation based on what you learned - Production AI engineering: You have shipped end-to-end AI-powered features used by real users, including integrating LLM APIs and working with concepts such as agents, prompts, and state management - AI Trust tooling: You have worked with tools such as LangSmith, Langfuse, Braintrust, or LangGraph, or with areas such as tracing, observability, governance, auditability, explainability, or safety - Full-stack product engineering: You have hands-on experience building production web products with TypeScript, Node.js, frontend technologies, and APIs - Product judgement and user focus: You can translate AI capabilities and evaluation results into practical product decisions that improve the user experience - Iterative problem solving: You’re comfortable working in a fast-moving area where best practices are still evolving, and you can test, learn, and adapt quickly ### Nice-To-Haves Quantitative evaluation skills: You’re comfortable applying statistical or mathematical reasoning to interpret evaluation results and compare system performance. - Applied AI/ML depth: You have experience with areas such as RAG, fine-tuning, datasets, experimentation, or broader applied machine learning - Research-driven problem solving: You’re comfortable learning from research papers, technical talks, experiments, and conversations with external experts when established answers do not yet exist. n8n is an ## About the company We give technical teams the freedom of code with the speed of no-code, so they can automate faster, smarter, and without limits. Backed by a fiercely inventive community and 500+ builder-approved integrations, we’re changing the way people bring systems together and scale ideas for impact. Since our founding in 2019, we’ve grown into a diverse team of over 260 - working across Europe and the US, connected by a shared builder spirit and with our centre of gravity in Berlin. Along the way, we’ve: - Cultivated a community of more than 650,000 active developers and builders - Earned 190K+ GitHub stars, making us one of the world’s Top 40 most popular projects - Backed by top investors, from Sequoia’s first German seed to our SAP's recent strategic investment - bringing us to a $5.2bn valuation That’s the company we’ve built. Now we’d love to see what you can build. If you’re applying, try n8n out - whether you’re technical or not - and share a screenshot of your first workflow with us. The easiest place to start is here: app.n8n.cloud/register http://app.n8n.cloud/register. We’re in a defining moment of an incredible journey. Come and build with us. 🎯 Your main goal will be to build the evaluation, reliability, and trust foundations that help n8n and its customers use AI-powered workflows with confidence. You’ll join the AI Trust team, focused on giving both customers and internal teams confidence in the AI features n8n is building. Today, that means designing and improving evals, benchmarks, observability, and quality feedback loops for AI-powered workflows and agents. Over time, it will also create the foundation for broader Trust capabilities such as auditability, governance, explainability, and safer production AI systems ### Build And Own Ai Evaluations Build and improve on the internal n8n eval platform and eval harnesses supporting AI-powered features and agents. - Implement the tools needed to define measurable signals for quality, correctness, reliability, regressions, and user value - Establish repeatable evaluation approaches that can be used by multiple teams throughout the AI feature development lifecycle ### Improve Ai Systems After Launch …

See the listing for full requirements.