Senior Full-Stack AI Engineer (LLMs & Agentic Systems)

About NebulAt Nebul, we’re building Europe’s sovereign AI cloud — trusted, secure, and purpose-built for the next generation of intelligent infrastructure.On top of this foundation, we’re building AI-native applications in two equally importantdirections: internal AI agents that improve how Nebul operates, and forward-deployed AI systems tailored to client environments and real-world use cases. These intelligent systems reason, automate, and collaborate with humans using large language models (LLMs).What You’ll Be DoingAs a Full-Stack AI Engineer, you’ll design and build production-grade AI applications across two core areas: roughly 50% internal AI agents for Nebul’s own teams and workflows, and 50% forward-deployed AI solutions for client use cases.This means you’ll work on internal systems that enhance productivity, decision-making, and automation across the company, while also building client-facing AI applications that are embedded into customer contexts, processes, and infrastructure.You’ll work across backend systems, AI orchestration, and lightweight frontend layers to deliver scalable, observable, and reliable AI systems. Your focus will be on agent-based architectures, LLM integrations, and end-to-end automation flows rather than traditional CRUD applications.You’ll have significant autonomy in technical decisions, influence architectural direction, and help define best practices for building AI systems that are robust enough for both internal operations and external deployment.Key ResponsibilitiesDesign and build end-to-end AI applications that leverage LLMs for reasoning, automation, and decision-making across both internal and client-facing environments.Develop internal AI agents that support Nebul teams by automating workflows, augmenting operations, and improving access to knowledge and systems.Build forward-deployed AI solutions for client use cases, adapting architectures and workflows to customer-specific environments, requirements, and constraints.Implement agentic architectures using frameworks such as LangChain, LlamaIndex, and PydanticAI.Develop backend services and orchestration layers in Python and Go, with supporting components in TypeScript where needed.Build and maintain LLM-powered workflows that integrate with internal systems, client systems, APIs, and external tools.Apply strong prompt engineering practices to ensure reliability, safety, and predictable model behavior across different deployment contexts.Work hands-on with LLMs, embeddings, retrieval (RAG), and tool calling.Implement LLM observability using tools like Langfuse, including tracing, evaluation, and cost monitoring.Ensure AI systems are scalable, testable, secure, and production-ready.Collaborate with platform, product, security, and client-facing teams to align AI capabilities with infrastructure, compliance, and business needs.Take ownership of AI system architecture and continuously evolve it as usage, complexity, and customer requirements grow.What Your Day Will Not Look LikeBuilding mostly static UIs or traditional frontend-heavy applications.Writing experimental AI demos without production considerations.Working on isolated scripts with no architectural, operational, or customer impact.What You BringStrong experience as a full-stack or backend engineer with a clear focus on AI-driven systems.Hands-on expertise with Python, plus working knowledge of Go and TypeScript.Proven experience building applications that integrate with LLMs in production environments.Solid understanding of agent-based systems, workflow orchestration, and AI system design.Practical experience with prompt engineering, model selection, and LLM evaluation.Familiarity with LLM observability concepts such as tracing, monitoring, feedback loops, and cost control.The ability to operate effectively across both internal product development and client-facing delivery.An ownership mindset and the ability to design systems that scale beyond prototypes.Bonus Points If You HaveExperience deploying AI systems on cloud-native or Kubernetes-based platforms.Familiarity with RAG pipelines, vector databases, or embedding strategies.Experience designing developer-facing AI platforms, internal AI tooling, or client-specific AI deployments.Interest in reliability, safety, and governance of AI systems.Experience mentoring engineers or acting as a technical lead.Eligibility & Application InformationWe welcome non-native Dutch speakers to apply. However, to be eligible, you must:Have a valid work permit in the Netherlands.Reside in the Netherlands and be able to travel to the office near The Hague.Be fluent in English (Dutch is not required).Ready to build production-grade AI systems that go beyond demos?Apply now through Frank Poll and help Nebul shape the future of intelligent, sovereign AI applications.