Senior Deep Learning Engineer

Job Summary

Focusing on the design and optimization of GPU-accelerated software, the full-time Senior Deep Learning Engineer specializing in Inference will enhance high-performance open-source frameworks for large-scale model serving and inference in a remote setting.

Key responsibilities

• Optimize and tune deep learning models for performance across various domains, including LLM and Generative AI
• Scale performance of deep learning models on different NVIDIA accelerator architectures
• Contribute to NVIDIA's inference libraries and collaborate with cross-functional teams on innovative solutions

Required qualifications

• Master's or PhD in Computer Engineering, Computer Science, EECS, AI, or equivalent experience
• 5+ years of relevant software development experience
• Proficiency in C/C++ programming and software design; Python experience is a plus
• Experience with training, deploying, or optimizing deep learning models in production
• Familiarity with GPU programming (CUDA, OAI TRITON, or CUTLASS) is advantageous