Senior Deep Learning Tools Engineer – CUDA Tile

Nvidia
US, CA, Santa Clara / US, UT, Remote / US, CA, Remote2026-05-06remote_local

About the job

NVIDIA is building advanced compiler technologies to accelerate AI workloads, and we are looking for an engineer focused on performance validation, analysis, and tracking. In this role, you will work at the intersection of deep learning compilers, GPU systems, and automation infrastructure, ensuring that performance improvements are measurable, scalable, and continuously validated over time.

Responsibilities

Design and develop performance testing frameworks for deep learning compilers and workloads

Build and maintain automated pipelines (CI/CD) to continuously track performance across models, hardware, and compiler changes

Implement benchmarking systems to measure latency, throughput, and efficiency of AI and HPC workloads

Analyze performance trends over time and identify regressions, bottlenecks, and optimization opportunities

Partner with compiler and architecture teams to debug and resolve performance issues

Develop tools and dashboards for performance visualization, reporting, and insights

Enable scalable testing across diverse GPU systems and environments

Improve infrastructure to ensure reliable, reproducible, and high-signal performance data

Qualifications

Minimum

BS, MS, or PhD (or equivalent experience) in Computer Science, Computer Engineering, Electrical Engineering, Mathematics, or related field

5+ years of software engineering experience, including experience in performance engineering, benchmarking, or systems optimization

Strong programming skills in Python (C++ is a plus)

Experience with CI/CD systems and automation frameworks

Familiarity with hardware-aware performance analysis (GPUs, accelerators, or similar systems)

Experience working with deep learning frameworks such as PyTorch, TensorFlow, JAX, or TensorRT

Background in data analysis, profiling, and regression tracking

Ability to debug complex system-level issues across software and hardware layers

Preferred

Experience with GPU performance analysis and optimization

Understanding of compiler internals (LLVM, MLIR, CUDA compilation flow)

Experience building performance dashboards and large-scale telemetry systems

Familiarity with hardware/software co-design or low-level performance tuning

Experience with distributed testing infrastructure or large-scale benchmarking systems