Senior Staff Engineer - ML Inference

Job Summary

Driving the advancement of machine learning, the remote Senior Staff Engineer - ML Inference will architect and optimize high-performance ML inference systems, ensuring rapid deployment and efficiency for millions of merchants.

Key responsibilities

• Architect, optimize, and own production ML inference for high throughput and ultra-low latency
• Leverage technologies like CUDA and TensorRT to achieve state-of-the-art performance at scale
• Collaborate with ML, infrastructure, and product teams to deploy and scale cutting-edge models

Required qualifications

• Proven expertise in building and optimizing large-scale ML inference systems
• Deep experience in production model serving and runtime optimization, especially with GPUs
• Strong software engineering skills in Python, C++, or other relevant languages
• Demonstrated leadership in architecting reliable, real-time inference systems
• Advanced understanding of model compression and deployment trade-offs