Staff / Principal Machine Learning Engineer, Serving - Switzerland

📋 Description

• Lead real-time inference optimization for serving
• Implement model acceleration: quantization, distillation
• Optimize performance on GPUs (C++, CUDA, Rust, Python)
• Build scalable distributed systems (Kubernetes, Ray)
• Own end-to-end deployment from research to prod
• Collaborate with cross-geo teams and leadership

🎯 Requirements

• Inference optimization: vLLM or TRT-LLM
• Model acceleration: quantization, distillation, caching, batching, paged attention
• High-performance systems: C++, CUDA, Rust, Python; GPU profiling
• Distributed systems: Kubernetes, Ray, load balancing, multi-GPU/multi-node
• Public work: OSS contributions to major inference engines
• Background: PhD in CS/Physics/Math or equivalent experience

🎁 Benefits

• Flat structure, fast iterations
• Open-source contributions encouraged
• Impact-focused culture with visibility of work
• Remote work within Switzerland