Compiler Debug Verification Engineer

Details

NVIDIA has been transforming Artificial Intelligence, computer graphics, PC gaming, and accelerated computing for more than 25 years. As an NVIDIAN you'll be immersed in a diverse, supportive environment where everyone is inspired to do their best work.

Role overview

This role is at the forefront of compiler verification, ensuring new compiler technology maintains premier standards. The role involves investigating object files and executables produced by compute and DSL compilers, working with debugger internals and debug information, analyzing performance and functional regressions, and automating compiler testing and reporting.

Responsibilities

• Investigate object files and executables generated by compute and DSL compilers; design and enhance tools to inspect them.
• Work with debugger internals and debug information for correctness and efficiency.
• Analyze performance degradation and functional defects in compute and DSL compilers; identify root causes, suggest corrective actions, and perform reviews to continuously improve testing.
• Automate compiler testing using NVIDIA test frameworks and programming: test execution, reporting, results analysis, and automation of build and test environments.
• Collaborate with software compiler developers to provide automated solutions for unit testing.
• Apply iterative planning and test development processes; identify gaps in test coverage and close them.

Requirements

• Bachelor's or Master's degree in Computer Science / Computer Engineering or equivalent experience.
• 3+ years' work experience in a software development or test organization.
• Deep understanding of Software Development Life Cycle (SDLC), High-Performance Computing (HPC), and software testing methodologies.
• Expertise in compilers and low-level software tools; demonstrated ability to solve problems and implement solutions in this domain.
• Ability to simplify sophisticated code to reproducible errors with minimal external dependencies.
• Experience writing test plans, developing tests, automating tests, executing tests, and reporting in a production environment.
• Proficiency in programming and/or testing using C, C++, CUDA, and Python.
• Knowledge of deep learning frameworks such as PyTorch, TensorRT, JAX, and Numba is highly desired.
• Excellent communication skills, self-motivated, and well-organized.

Ways to stand out

• 5+ years' experience testing production software, preferably compilers or other system software.
• Experience with the LLVM project, MLIR, LLVM IR; debuggers like GDB and LLDB; and ELF and DWARF standards.
• Previous experience in compiler development, verification/testing, or performance analysis; plus unit-test development in system software.
• Proficiency with the NVIDIA CUDA Toolkit, especially solving issues and debugging in a Linux environment.
• Experience with revision control and management tools such as Git, Perforce, JIRA, Confluence, and Make.

Compensation & benefits

• Base salary range: 136,000 USD - 212,750 USD (final base determined by location, experience, and pay of employees in similar positions).
• Eligible for equity and company benefits (see NVIDIA benefits page).

Other details

• Employment type: Full time
• Application window at least until August 10, 2025
• NVIDIA is an equal opportunity employer and values diversity in its employees.