Software Engineer, Model Inference

OpenAI is hiring a Senior Software Engineer for their Model Inference team. This role focuses on optimizing large AI models for high-volume, low-latency production and research environments. Responsibilities include collaborating with researchers and product managers, improving inference stack performance, and optimizing hardware utilization.

Skills and focus areas

• model inference optimization
• machine learning architectures
• performance optimization
• latency optimization
• throughput optimization
• efficiency optimization
• bottleneck identification
• instability analysis
• code optimization
• hardware optimization
• pytorch
• nvidia gpu