Agentic Tooling Engineer EU/UK remote (m/f/d) remote

Role overview

Build and operate shared infrastructure for an internal framework that helps engineering teams use AI agents to take work from idea to production. The framework is treated as a product, with real users, versions, evaluations, and measurable outcomes. You will shape its reliability and adoption by combining hands-on tooling work with system design, evaluation, and collaboration across developer experience and platform teams.

Responsibilities

- Maintain shared tooling for agent installation and distribution, reusable skills and agents, linting, evaluation runners, and connections between agent harnesses. - Help engineering teams build and maintain their own agent tools in line with framework requirements, and spread effective ideas across tools. - Create evaluations and certification processes to check whether changes to an agent harness improve results before release. - Move stable, rule-based steps into platform checks that run consistently across authors and tools. - Gather feedback from real usage, address sources of friction, and add checks to prevent recurring failures. - Drive adoption through pairing, training, and tracking delivery outcomes; improve the framework and help define new workflows and agents.

Requirements

- Deep, practical experience with multiple agentic development tools and the infrastructure they run on, including an understanding of their strengths and failure modes. - Experience building agent-related tools that other engineers use, such as skills, plugins, hooks, subagents, MCP servers, or custom agents. - Knowledge of LLM evaluation and context engineering, including evaluating non-deterministic systems and diagnosing failure traces. - At least seven years of production software engineering experience, including developer tooling or an internal platform with real users. - Strong system design and verification judgment: able to decide which controls need deterministic checks and which can rely on a model. - Strong Python, Git, and GitHub skills; able to read Java and Kotlin comfortably. - Precise technical writing and the ability to influence engineering practices across teams.

Nice to have

- At Staff level, experience setting technical direction across several teams. - Background in a regulated industry such as payments or banking, security engineering, or maintaining an open-source project.

Benefits and work setup

- Remote work flexibility and choice of Windows or Mac. - Monthly mobility support, a Wellhub membership, and a monthly product card credit. - A collaborative environment with transparent communication and opportunities to develop professionally.