Tech Stack

Description

You will design and develop customer-facing multi-modal ML inference systems for creative generative AI applications, leveraging cutting-edge optimization techniques and high-performance computing resources to push the boundaries of what's possible.

Requirements

• 7+ years productionizing machine learning systems including inference pipelines
• Expert-level Python for scalable services
• 5+ years with PyTorch and high-performance inference frameworks (e.g., Triton, TensorRT)
• Deep understanding of diffusion model architectures
• Experience profiling and optimizing neural networks on Nvidia GPUs (e.g., Nsight)

Responsibilities

• Lead design and development of customer-facing multi-modal ML inference systems
• Build inference systems for next-generation models, focusing on optimization and deployment
• Partner with cloud providers to deliver hosted inference solutions
• Prototype and productionize inference platform improvements and new features
• Drive business impact through strategic thought partnership across the organization