Senior Machine Learning Engineer, LLM Inference Optimization

Sourced from springcube.com

SpringCube is hiring a Senior Machine Learning Engineer focused on LLM inference optimization. The role owns optimization projects across model families and inference backends, improving latency and throughput for LLM and VLM endpoints. You will also develop model compression workflows and benchmark inference engines.

• Own optimization projects for model families and inference backends
• Improve latency and throughput for LLM/VLM endpoints
• Develop model compression workflows
• Configure and benchmark inference engines

• Experience optimizing LLM/VLM inference
• Hands-on with inference engines and benchmarking
• Knowledge of model compression techniques
• Strong machine learning engineering background