Base: 152,000 usd - 218,500 usd for level 3, 184,0...
Deep learning and neural networks inference
Performance profiling and optimization
Gpu-based application expertise
This role offers an opportunity to directly impact the hardware and software roadmap in a fast-growing technology company that leads the AI revolution
Job Summary
This role offers an opportunity to directly impact the hardware and software roadmap in a fast-growing technology company that leads the AI revolution.
You will implement language and multimodal model inference as part of NVIDIA Inference Microservices and contribute to NVIDIA’s open-source inference serving library.
The position involves collaborating heavily with other software and hardware co-design teams to enable the creation of the next generation of AI-powered services.
Matching Summary
This role offers an opportunity to directly impact the hardware and software roadmap in a fast-growing technology company that leads the AI revolution.
Salary
Base: 152,000 USD - 218,500 USD for Level 3, 184,000 USD - 287,500 USD for Level 4; Bonus/Equity: Eligible for equity; Benefits: Eligible for benefits
Skills & Requirements
Must-have
Deep learning and neural networks inference
Performance profiling and optimization
GPU-based application expertise
Proficient in C++ and PyTorch
Understanding of GPU architecture
Nice-to-have
Processor and system-level performance optimization
Knowledge of modern LLM architectures
GPU programming experience with CUDA or OpenCL
Strong algorithm fundamentals
Key Requirements
PhD in CS, EE or CSEE or equivalent experience
3+ years of relevant experience
Experience with GPU-based performance optimization