Senior / Lead Machine Learning Engineer, Serving - Germany

📋 Description

• Lead the development and optimization of real-time ML serving systems at scale.
• Containerize research models and ensure reliable production deployment.
• Collaborate with US leadership to translate research into production tooling.
• Drive latency, throughput, and reliability improvements across deployments.

🎯 Requirements

• Inference optimization with modern serving frameworks (vLLM, TRT-LLM).
• Model acceleration: quantization, distillation, caching, batching, paging attention.
• High-performance systems: C++, CUDA, Rust, or optimized Python; GPU profiling.
• Distributed systems: Kubernetes, Ray; multi-GPU/multi-node inference; thousands of connections.
• Public work: open-source contributions to major inference engines.
• PhD or equivalent experience; English fluency in written and spoken.