Senior DL Inference & Performance Engineer

NVIDIA Corporation; Santa Clara (CA); Hybrid; USD 184,000 - 287,500; Full time

Job summary

A leading technology company in California is seeking a Senior DL Algorithms Engineer to drive inference performance for Deep Learning workloads. The role involves implementing advanced model inference and collaborating with co-design teams to optimize performance across hardware and software interfaces. Candidates should hold a PhD in a relevant field and have over 5 years of experience in deep learning and GPU programming. This position offers a competitive base salary ranging from $184,000 to $356,500 depending on experience.

Qualifications

• 5+ years of experience in deep learning and neural networks, especially in inference.
• Experience with performance profiling and optimization for GPU-based applications.
• Deep understanding of computer architecture and fundamentals of GPU architecture.

Responsibilities

• Implement language and multimodal model inference.
• Contribute new features and deliver production code to TRT-LLM.
• Profile and analyze bottlenecks across the inference stack.

Skills

Deep learning

C++

Performance analysis

Neural networks

GPU programming

PyTorch

Education

PhD in CS, EE or CSEE or equivalent experience

Job description

A leading technology company in California is seeking a Senior DL Algorithms Engineer to drive inference performance for Deep Learning workloads. The role involves implementing advanced model inference and collaborating with co-design teams to optimize performance across hardware and software interfaces. Candidates should hold a PhD in a relevant field and have over 5 years of experience in deep learning and GPU programming. This position offers a competitive base salary ranging from $184,000 to $356,500 depending on experience.