NVIDIA
Technology
SeniorDeepLearningToolsEngineer–CUDATile
Neural analysis suggests this role is
optimal for Senior candidates.
“Senior Deep Learning Tools Engineer – CUDA Tile at NVIDIA. Skills: Deep Learning Compiler & Tools Engineering, Performance Engineering, CUDA, GPU Systems, Automation Infrastructure. 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”
What You'll Achieve.
Ensuring that performance improvements are measurable, scalable, and continuously validated over time; Drive the performance of next-generation compilers; Build systems that track, analyze, and improve performance across rapidly evolving AI workloads; Ensure reliable, reproducible, and high-signal performance data
Industry & Context.
Debug complex system-level issues across software and hardware layers; Identify regressions, bottlenecks, and optimization opportunities; Debug and resolve performance issues
What They're Looking For.
Must Have
5+ years of software engineering experience, experience in performance engineering, benchmarking, or systems optimization, programming skills in Python, 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
Nice to Have
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, C++ programming skills
What You'll Do.
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
Implement benchmarking systems to measure latency
and efficiency of AI and HPC workloads
Analyze performance trends over time and identify regressions
and optimization opportunities
Partner with compiler and architecture teams to debug and resolve performance issues
Develop tools and dashboards for performance visualization
Enable scalable testing across diverse GPU systems and environments
Improve infrastructure to ensure reliable
and high-signal performance data
How You'll Work.
Team & Collaboration
Collaborate closely with compiler developers, infrastructure providers, and hardware teams; Partner with compiler and architecture teams
Full Job Description
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. Do you want to help drive the performance of next-generation compilers? Are you excited by how GPU performance powers breakthroughs in deep learning, autonomous systems, and high-performance computing? We are seeking a talented Deep Learning Compiler & Tools Engineer focused on CUDA Tile (Performance & Infrastructure) to join our team. You will collaborate closely with compiler developers, infrastructure providers, and hardware teams to build systems that track, analyze, and improve performance across rapidly evolving AI workloads. If you're passionate about performance, systems, and building infrastructure that drives real-world impact, we want to hear from you. **What You’ll Be Doing:** * 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 **What We Need to See:** * BS, MS, or PhD (or equivalent experience) in Computer Science, Computer Engineering, Electrical Engineering,
Applying for this Senior Deep Learning Tools Engineer – CUDA Tile role?
Most applicants get filtered before a human reads their resume. See if yours makes the cut.
How to Apply on Workday
- Workday has a multi-step form — save your progress after every section.
- "Apply With LinkedIn" can fail or lose data; manual entry is more reliable.
- Watch for the "Submit for Review" final step — hitting "Save" alone does not submit.
- Job requisition numbers are useful when following up with HR by email.
ANONYMOUS · UNFILTERED
What do employees actually say about NVIDIA?
Real rants from real employees. Read before you apply.