Description
NVIDIA is hiring a Software Engineer, AI Inference Systems to architect and implement high-performance inference stacks, optimize GPU kernels and compilers, benchmark ML inference systems, and orchestrate large-scale containerized deployments across GPU clusters and cloud environments. The role involves contributing to vLLM, developing GPU programming and compiler infrastructure, supporting MLPerf Inference, and publishing research. Candidates need a bachelor’s, master’s, or PhD in a relevant field with substantial experience, strong Python and C/C++ skills, GPU and performance-engineering expertise, and experience with containers and orchestration. The position is hybrid and offers base salary in Poland of 292,500–507,000 PLN for Level 4 and 375,000–650,000 PLN for Level 5.
