Senior Machine Learning Engineer, LLM Inference Optimization

Sourced from hubmub.com

This senior role focuses on optimizing large language and vision-language model inference for production deployment. The engineer will work across model internals, inference engines, and serving architectures to improve performance and efficiency. Key responsibilities include benchmarking and deploying optimized models.

• Optimize LLM and vision-language model inference pipelines
• Work with model internals and inference engines
• Design and implement serving architectures
• Conduct benchmarking for model performance

• Experience with LLM inference optimization
• Strong background in machine learning engineering
• Knowledge of model deployment and serving architectures