Software Engineer, Model Inference

OpenAI is seeking a Senior Software Engineer for their Model Inference team, focusing on optimizing the world's largest AI models for production use. This role sits at the intersection of cutting-edge AI research and practical implementation, working within the Scaling department to make OpenAI's most capable models accessible through their products.

The position offers a competitive compensation package of $325K-$490K plus equity and comprehensive benefits, including medical coverage and parental leave. Based in San Francisco, you'll be part of a team that brings state-of-the-art AI models to consumers, enterprises, and developers.

The ideal candidate brings 5+ years of software engineering experience, with expertise in distributed systems and ML architecture optimization. You'll work on high-stakes challenges, optimizing performance, latency, and efficiency of model inference systems. Key responsibilities include collaborating with researchers and product managers, implementing new architectural improvements, and ensuring optimal hardware utilization.

This role is perfect for someone who combines technical depth with practical problem-solving abilities. You'll need familiarity with PyTorch, GPU optimization, and HPC technologies. The position offers unique opportunities to impact AI development at scale, working with cutting-edge technology while ensuring it benefits humanity. OpenAI's commitment to safety and human-centric AI development makes this an opportunity to contribute to responsible AI advancement.