Senior AI Inference Engineer - High-Performance GPU Systems

NVIDIA; Lavamünd; Vor Ort; EUR 120.000 - 160.000; Vollzeit

Zusammenfassung

NVIDIA seeks highly skilled software engineers to build AI inference systems that scale models efficiently. You will architect and implement high-performance stacks, optimize GPU kernels and compilers, and drive benchmarks across multi-GPU, multi-node, and multi-cloud environments.

You will collaborate with inference, compiler, scheduling, and performance teams to push the frontier of accelerated AI computing while delivering practical, production-ready software across NVIDIA’s platforms.

Qualifikationen

• Bachelor’s degree in Computer Science, Computer Engineering or Software Engineering with 7+ years of experience; or Master’s 5+ years; or PhD with strong ML Systems publications.
• Strong programming skills in Python and C/C++; knowledge of Go or Rust is a plus.
• Deep fundamentals in algorithms, data structures, OS, architecture, parallel/distributed systems and DL theory.
• Familiarity with performance engineering in ML frameworks (e.g., PyTorch) and inference engines (e.g., vLLM).
• Experience with GPU programming, CUDA, memory hierarchies, and profiling tools (Nsight).

Aufgaben

• Contribute features to vLLM and optimize inference frameworks for new NVIDIA GPUs.
• Develop, optimize, and benchmark GPU kernels using fusion, autotuning, and memory/layout optimization.
• Define benchmarking methodologies and contribute to MLPerf Inference submissions.
• Architect scheduling and orchestration of containerized large-scale inference deployments on GPU clusters.
• Publish original research and translate ideas into NVIDIA software products.

Kenntnisse

Python

C/C++

Go or Rust

Algorithms & data structures

Parallel programming

Distributed systems

Performance engineering

GPU programming

CUDA

Nsight (Systems/Compute)

Containerization

Linux namespaces & cgroups

Communication skills

Ausbildung

Bachelor’s degree in CS/CE/SE

Master’s degree in CS/CE/SE

PhD in ML Systems / GPU architecture / HPC

Tools

TorchDynamo/Inductor

Triton

MLIR/LLVM

CUTLASS

XLA

ML tooling (Nsight)

Jobbeschreibung

NVIDIA seeks highly skilled software engineers to build AI inference systems that scale models efficiently. You will architect and implement high-performance stacks, optimize GPU kernels and compilers, and drive benchmarks across multi-GPU, multi-node, and multi-cloud environments.

You will collaborate with inference, compiler, scheduling, and performance teams to push the frontier of accelerated AI computing while delivering practical, production-ready software across NVIDIA’s platforms.