2 days ago
Base Salary
$224k - $357k/yr
Responsibilities
- Develop GPU-accelerated AI inference serving software.
- Contribute to feature development and drive broad customer adoption.
- Drive convergence of the Triton Inference Server and NVIDIA Dynamo stacks into a unified inference platform.
- Support high-performance serving for LLM and non-LLM workloads.
- Build robust production software for server and cloud environments.
- Optimize prediction throughput and latency and adopt next-generation inference technologies.
- Participate in the open-source deep learning software engineering community.
Requirements
- MS or PhD in Computer Science or a relevant field, or equivalent experience.
- 12+ years of professional experience working on deep learning software.
- Excellent Rust and C++ skills, familiarity with Python, and strong software design, debugging, performance analysis, and test design skills.
- Experience with high-scale distributed systems and ML systems.
- Strong communication skills and ability to work in a fast-paced agile team environment.
- Preferred experience with TensorRT, PyTorch, ONNX, OpenVINO, vLLM, or TRT-LLM.
- Preferred knowledge of GPU memory management, cache management, high-performance networking, and distributed systems programming.
- Preferred experience contributing to large open-source projects, including GitHub, bug tracking, branching and merging, open-source licensing, and patch handling.
Benefits
- Hybrid work arrangement.
- Eligible for equity and benefits.
About Nvidia
Nvidia designs and sells GPUs and accelerated computing platforms for data centers, AI/ML, graphics, gaming, and automotive, monetizing through hardware, software platforms (CUDA, AI frameworks), and systems like DGX and networking. Customers include cloud providers, enterprises, researchers, and OEMs. Founded in 1993 and headquartered in Santa Clara, it is a public company traded on NASDAQ under NVDA.