Senior Agent Platform Engineer

Munich. Posted 2 months ago

The role

You will be the technical owner of the AI agent platform. You will design, deliver, and operate the platform architecture, runtime, and integration layers to support physicists and engineers.

What you will do

Own the design, delivery, and operation of the agent platform
Turn the agent ecosystem into stable platform building blocks
Co-design the integration layer connecting agents to internal and external systems
Make autonomy safe and governable through permission flows and audit logging
Build the evaluation and observability layer for non-deterministic systems
Operate the platform on Google Cloud with production discipline
Work with technical users to feed feedback into the platform roadmap

Required qualifications

5+ years of software engineering experience
Real depth in Python and distributed backend systems
Architected, built, and operated production-grade agentic or LLM systems
Hands-on knowledge of the agent ecosystem including MCP, agent SDKs and CLIs, multi-agent orchestration patterns, and sandboxed code execution
Experience running production workloads on Kubernetes and a major cloud
Experience with infrastructure as code (Terraform) and CI/CD

Nice to have

Experience with model gateways and routing
Exposure to scientific or high-performance computing: batch schedulers, HPC clusters, or simulation-heavy environments
Open-source contributions to AI/agent tooling
A track record of technical mentorship

Before you apply

Recruiter Interview (30-60 min)
Technical Screening (30 min)
Technical Panel (3x60 min)
CEO call (30min)

About the company

Proxima Fusion is a fusion company developing hardware and infrastructure for a commercial stellarator fusion power plant. The team is based across Munich, Zurich, and Oxford.