Opportunity Description
Step into a leadership role at NVIDIA as a Senior Engineer specializing in AI inference systems. Your expertise will enhance performance across large-scale AI models using advanced GPU technologies.
As a vital part of the team, your deep technical acumen in software engineering will influence AI frameworks. Focus on optimizing inference stacks while contributing to pioneering research and building effective tools for developers to harness GPU capabilities.
Key Responsibilities:
• Design features for AI models utilizing vLLM
• Benchmark and optimize GPU compilers and kernels
• Define strategies for inference benchmarking
• Manage orchestration of inference deployments
• Explore and integrate cutting-edge ML research ideas
Requirements:
• PhD or 7+ years of relevant industry experience
• Expert in Python and C/C++, especially in performance
• Understanding of GPU programming techniques
• Experience in Docker and Kubernetes orchestration
• Strong ski...
As a vital part of the team, your deep technical acumen in software engineering will influence AI frameworks. Focus on optimizing inference stacks while contributing to pioneering research and building effective tools for developers to harness GPU capabilities.
Key Responsibilities:
• Design features for AI models utilizing vLLM
• Benchmark and optimize GPU compilers and kernels
• Define strategies for inference benchmarking
• Manage orchestration of inference deployments
• Explore and integrate cutting-edge ML research ideas
Requirements:
• PhD or 7+ years of relevant industry experience
• Expert in Python and C/C++, especially in performance
• Understanding of GPU programming techniques
• Experience in Docker and Kubernetes orchestration
• Strong ski...
Interested in this opportunity? Apply now through Expertini.
Apply for this Position