Staff / Senior Staff Machine Learning Engineer, Inference - Switzerland

Staff/Principal Machine Learning Engineer focused on serving at Inworld.ai. This role involves optimizing real-time inference for state-of-the-art voice models, requiring deep understanding of modern serving frameworks and model acceleration techniques.

Skills and focus areas

• inference optimization
• serving frameworks
• vllm
• trt-llm
• model acceleration
• quantization
• distillation
• caching strategies
• continuous batching
• paged attention
• speculative decoding
• high-performance systems