View All Jobs 2615
Software Engineer, Model Inference
Optimize the world's largest AI models for efficient production deployment and performance.
San Francisco, California, United States
Mid-Level
1 month ago
✨ About The Role
- The role involves optimizing large AI models for high-volume, low-latency production environments.
- The engineer will collaborate with machine learning researchers, engineers, and product managers to deploy the latest technologies.
- Responsibilities include introducing new techniques and tools to enhance model performance and efficiency.
- The engineer will build tools to identify bottlenecks and design solutions to address them.
- Code optimization and efficient utilization of Azure VMs are key tasks in this position.
âš¡ Requirements
- The ideal candidate has a strong understanding of modern machine learning architectures and optimization techniques, particularly for inference.
- They should possess at least 3 years of professional software engineering experience.
- Familiarity with PyTorch, NVidia GPUs, and related software stacks is essential.
- The candidate should have experience in architecting, observing, and debugging production distributed systems.
- A humble attitude and eagerness to assist colleagues are important traits for success in this role.
Software Engineer, Model Inference
San Francisco, California, United States
Engineering
About OpenAI
Building artificial general intelligence