Senior Software Engineer, GPU Code Generation for Machine Learning Inference

What you’d do

Develop advanced GPU inference software for TensorRT focusing on GPU code generation, just-in-time compilation, and inference optimization to improve performance of generative AI models on NVIDIA GPUs. Full-time position in Santa Clara, CA. Found on the employer's careers page on Oct 21, 2026. Apply through the link.

You’ll need

• Experience in GPU optimization
• Experience in compiler development
• Knowledge of GPU execution
• Full-time availability
• Experience with AI inference software