Take on an exciting position at NVIDIA as a Software Engineer specializing in AI inference. This hybrid role focuses on architecting high-efficiency inference software using advanced GPU techniques. We are searching for motivated software engineers with robust programming skills and a background in ML frameworks.

Your role will involve optimizing performance through innovative features in vLLM and developing GPU kernels. Collaborating with diverse teams, you will push the limits of accelerated computing technology. Key Responsibilities:

- Develop features for vLLM with NVIDIA GPU hardware
- Optimize framework using advanced engineering methods
- Conduct original research on ML Systems and techniques
- Implement benchmarking and runtime optimizations
- Handle profiling and debugging of GPU applications Requirements:
- Bachelor’s, Master’s, or PhD in Computer Science field
- Minimum 5 years of relevant experience
- Strong grounding in algorithms and data structures
- Familiarity with CUDA and GPU programming
- Excellent problem-solving and communication skills Leverage your software engineering skills at NVIDIA and impact AI's future.

📌 NVIDIA Software Engineer for AI Inference (Toronto)
🏢 NVIDIA
📍 Toronto