Lead Platform Engineer (m/f/d)

Role overview Take ownership of the infrastructure that powers a real-time conversational AI platform as Lead Platform Engineer. You will manage large-scale GPU deployments across multiple clouds and regions, architect the systems behind low-latency AI experiences, and set the technical direction for how the platform builds and scales. The role also drives cross-functional compliance and security certification work alongside engineering, product, and operations teams.

Responsibilities - Manage deployments of thousands of concurrent GPU servers across multiple clouds, with a sharp focus on performance and efficiency - Architect and implement systems for dynamic deployment, routing, and load balancing across regions - Design and ship scalable, reliable deployment pipelines that are pleasant to operate - Set technical direction for infrastructure decisions and raise the engineering bar across the team - Champion simple, robust tooling by researching, documenting, and driving adoption - Own observability and monitoring so incidents are detected and resolved quickly - Lead compliance and security initiatives including SOC 2 Type II, coordinating across engineering, product, and operations - Hold a high bar for testable, operable, and maintainable software across everything that ships

Requirements - 5+ years of hands-on production experience with AWS - Proficiency in TypeScript or Go - Strong Infrastructure-as-Code skills with AWS CDK, Pulumi, or Terraform - Working knowledge of at least one additional major cloud platform (Azure, GCP, or Oracle OCI) or on-premise deployments - Deep expertise in serverless architectures and security best practices - Solid understanding of containerization and Docker in real production environments - Experience designing globally distributed, low-latency systems - Comfort working in a fast-paced startup environment with strong ownership from day one - Clear written and verbal English communication, able to explain infrastructure decisions to non-technical audiences

Nice to have - Experience with AI/ML workloads and GPU infrastructure - Specific AWS CDK expertise - Background in systems or graphics programming - Familiarity with the Wine/Proton/VKD3D ecosystem

Benefits and work setup - Remote-friendly within CET ±2 hours, with a Berlin office available for local staff - 28 days paid vacation plus one mental health day per year - €900 annual education budget and home office equipment provided - Small team with direct collaboration with the founders and high individual impact