Senior/Staff Software Engineer - Machine Learning Platform (Inference)

Responsibilities

• Help define and own the roadmap for platforms and tools enabling state-of-the-art machine learning on Snowflake
• Build and execute a vision for incorporating new advances in machine learning to achieve business objectives
• Ensure operational excellence, reliability, availability, and performance of services
• Collaborate across ML partner teams to improve development velocity and capabilities
• Support team members in delivering high technical quality

Requirements

• 7+ years of industry experience designing and supporting Internet serving infrastructure or ML platforms
• Strong track record with machine learning systems and platforms
• Experience serving LLMs using inference engines like vLLM, TensorRT-LLM, TEI, or SGLang
• Experience serving fine-tuned LLMs (PEFT, DPO, RL)
• Experience with frameworks such as SKLearn, XGBoost, PyTorch, TensorFlow, or MLflow
• Experience building batch and real-time ML serving systems
• Proven ability to lead technical decision making and roadmap development
• BS/MS/PhD in Computer Science or related field, or equivalent experience

About the Company

Snowflake's Machine Learning Platform team aims to enable customers to bring machine learning and deep learning workloads to Snowflake by building highly integrated, scalable, and secure platform solutions.