The role involves crafting robust inferencing software scalable across multiple platforms for NVIDIA's product lines
Job Summary
The role involves crafting robust inferencing software scalable across multiple platforms for NVIDIA's product lines.
Candidates must possess strong C/C++ or Python skills alongside experience with deep learning frameworks like PyTorch and TensorRT-LLM.
The team is fast-paced and delivery-focused, requiring excellent interpersonal skills and the ability to collaborate across research and product divisions.
Matching Summary
The role involves crafting robust inferencing software scalable across multiple platforms for NVIDIA's product lines.
Salary
Not specified; Not specified; Not specified
Skills & Requirements
Must-have
C/C++ or Python programming skills
Experience with PyTorch and TensorRT-LLM
Performance analysis and optimization expertise
Deep learning framework knowledge
Master's degree in Computer Science
Nice-to-have
Proactive ability to work without supervision
Excellent written and oral communication skills
Awareness of latest AI academic developments
Experience with SGLang and vLLM frameworks
Ability to publish results in scientific conferences
Key Requirements
Masters or higher degree in Computer Engineering or related field
2+ years of relevant software development experience
Strong curiosity about artificial intelligence and LLMs