Senior Agent Platform Engineer

WHO WE ARE Proxima Fusion is Europe’s fastest-growing fusion company and the continent’s best-funded fusion player, as well as the first spin-out from the Max Planck Institute for Plasma Physics (IPP). Backed by over €650M and powered by a growing team across Munich, Zurich, and Oxford, we are developing the hardware and infrastructure needed to deliver the world’s first commercial stellarator fusion power plant. Our concept advances the most mature fusion technology out there, the Wendelstein 7-X stellarator, through two next-generation machines: Alpha and Stellaris. Our work combines stellarator optimization, advanced computation, machine learning, and high-temperature superconducting magnets to unlock higher-performance designs that were previously out of reach. Turning these designs into a functioning fusion power plant requires excellence and ownership across every discipline, from physics and engineering to software, manufacturing, law, and business functions. WHY JOIN PROXIMA FUSION You will get to work on some of the most complex tech challenges to bring abundant, safe, clean energy to the world. You'll get to join and learn from an exceptional selection of accomplished and driven individuals. Do your life’s best work and enjoy the journey. Get to show that big things are possible in Europe when you assemble the best talent. YOUR IMPACT Technical owner of Proxima’s AI agent platform, turning autonomous agents into reliable everyday colleagues for physicists and engineers. Own the platform architecture, technical delivery, and day-to-day operation. Scale the platform from an early product into reliable, governed infrastructure used across the company. Enable agents to work across knowledge bases, write code, run simulations, and support engineering workflows. Work within the Enterprise AI Team Lead’s overall vision while owning how that vision is technically implemented. Use strong technical judgment to influence and shape the platform roadmap. Identify and propose new platform features based on hands-on experience and feedback from internal users. Build a platform that engineers and scientists can trust for real, production-level work.   WHAT YOU WILL DO Own the design, delivery, and operation of our agent platform: the runtime and its primitives: durable sessions, sandboxed execution environments, long-running task execution, memory, and tool integration Turn a rapidly evolving agent ecosystem into stable platform building blocks: evaluate harnesses, models, and protocols as they emerge, and decide what becomes a supported primitive versus a passing experiment Co-Design the integration layer that connects agents to internal and external systems, from enterprise tools to our scientific computing stack, and the standards for how tools, skills, and context are exposed to agents Make autonomy safe and governable: permission and approval flows with human-in-the-loop escalation, capability boundaries, audit logging, cost and token controls, and hardening against prompt injection and tool abuse Build the evaluation and observability layer for non-deterministic systems: session tracing, quality evals, and cost/latency visibility, so we know agents work before our users have to find out Operate what you build on Google Cloud with production discipline: reliability, failure handling, and observability Work directly with demanding technical users and feed their feedback and your technical judgment into the platform roadmap you shape together with the team lead WHO YOU ARE Must have You have 5+ years of software engineering experience, with real depth in Python and distributed backend systems You have architected, built, and operated production-grade agentic or LLM systems well beyond the prototype phase You know the current agent ecosystem hands-on: MCP, agent SDKs and CLIs, multi-agent orchestration patterns, sandboxed code execution and have formed opinions on wh