NVIDIA AI
US - California - Santa Clara
View Company Profile /
<< Go Back
Develop high-performance GPU-accelerated AI inference software and drive the convergence of the Triton Inference Server and NVIDIA Dynamo stacks. You will contribute to feature development while balancing throughput, latency, and production-grade deployment requirements.
Requirements: Requires an MS or PhD in Computer Science or equivalent experience with 12+ years in deep learning software. Candidates must possess excellent Rust and C++ skills, along with experience in high-scale distributed systems and ML frameworks.
Key Skills: Rust, C++, Python, Deep learning, GPU acceleration, Distributed systems, AI inference, Performance analysis, Debugging, Test design, LLM, TensorRT, PyTorch, ONNX, OpenVINO, vLLM
Benefits: Equity, Benefits
© 2026 engineeringjobs.net, Inc. All Rights Reserved.
Terms of Service | Privacy
Powered by JOBBEX