AI Inference Systems Engineer at NVIDIA

Join NVIDIA as a Senior Software Engineer focusing on AI Inference Systems. Contribute to cutting-edge GPU technologies and optimize inference frameworks utilizing your expertise in Python and C/C++.

NVIDIA is seeking a highly qualified engineer with 7+ years of experience and a solid background in software engineering, computer science, or computer engineering. The role emphasizes performance engineering in machine learning frameworks, particularly with PyTorch and vLLM. Become an integral part of a team that drives innovation through advanced GPU programming and optimizes inference engines for large-scale deployments.

Key Responsibilities:

• Contribute features to vLLM for GPU performance

• Optimize inference framework using various parallelism techniques

• Develop and benchmark GPU kernels for efficiency

• Build methodologies for industry-standard inference benchmarks

• Architect containerized large-scale inference deployments

Requirements:

• Bachelor’s degree with 7+ years experience in relevant fields

• Proficient in Python and C/C++, experience with Go/Rust

• Deep understanding of ML frameworks and inference engines

• Familiar with Docker, Kubernetes, and cloud platforms

• Excellent problem-solving and debugging skills

Utilize your programming and engineering skills to enhance NVIDIA's AI Inference Systems.
#J-18808-Ljbffr