Compiler Engineer

We are seeking an experienced Compiler Engineer to join the GPU Assembler team at NVIDIA. As a Compiler Engineer, you will play a crucial role in developing tools that enable the creation of high-performance applications and libraries for HPC, deep learning, and autonomous driving domains.

You will lead the design and development of NVIDIA's Assembler and Disassembler for GPU compute. Your responsibilities will include:

• Working on binary analysis and instrumentation features such as call graph generation, program register usage, and patching of GPU binaries
• Collaborating with GPU architecture and debugger/profiler development teams to understand their requirements and deliver new features and product improvements
• Working with customers and partners to collect feedback and drive innovative ideas and features to incorporate into the product
• Ensuring compatibility, reliability, and high-quality code generation by collaborating with teams developing other related components

To be successful in this role, you will need:

• A BS or MS degree in Computer Science, Computer Engineering, or related fields with 8+ years of experience in low-level system software development and a minimum of 6 years of development in compilers, assemblers, binary utilities, and binary analysis tools
• Good analytical and C/C++ programming skills
• Experience in any one area of compiler development, including feature support, code generation, and compiler infrastructure
• Good understanding of Assembly Language, Processor ISA (GPU ISA a plus), and processor architecture
• Knowledge of object file formats such as ELF and debugging formats (DWARF)

Preferred qualifications include:

• Understanding of debugger/profiler tools/bintools/linker internals, experience in binary analysis/instrumentation tools like BOLT, etc.
• Usage of AI tools in everyday work like Cursor, Codex, Claude, etc.
• Knowledge of GPU development and compute APIs such as CUDA and OpenCL