Back to search
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, 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
Ways to Stand Out from the Crowd::
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
With highly competitive salaries and a comprehensive benefits package, NVIDIA is widely considered one of the most desirable employers in the technology industry. Our teams are tackling some of the most challenging problems in AI, deep learning, and accelerated computing.
Your base salary will be determined based on your location, experience, and the pay of employees in similar positions. The base salary range is 152,000 USD - 241,500 USD.You will also be eligible for equity and benefits.
This posting is for an existing vacancy.
NVIDIA uses AI tools in its recruiting processes.
NVIDIA is committed to fostering a diverse work environment and proud to be an equal opportunity employer. As we highly value diversity in our current and future employees, we do not discriminate (including in our hiring and promotion practices) on the basis of race, religion, color, national origin, gender, gender expression, sexual orientation, age, marital status, veteran status, disability status or any other characteristic protected by law.#deeplearningLearn more about this Employer on their Career Site
