Senior Software Engineer, DL Compilers

NVIDIA • Redmond, WA

1d

About The Position

NVIDIA's GPUs are at the core of modern AI infrastructure, from training large-scale models to running inference in production. That position depends on software as much as hardware, and compiler engineering is a big part of what makes it work. We're hiring senior software engineers for a compiler team within NVIDIA's deep learning software organization. This team builds a code generation backend that connects frontend ML compilers to NVIDIA's GPU compilation and execution stack, targeting high-performance kernel generation for deep learning workloads. What you'll be doing: You'll work on the compiler infrastructure responsible for generating high-performance GPU kernels from frontend compiler representations. This spans the full codegen pipeline: taking in high-level graph operations, lowering them through intermediate representations, and producing efficient code targeting NVIDIA's GPU compiler backends. You may work at any layer of this stack, from the interface with compiler frontends down to the tile-level IR and code generation machinery underneath. Designing and implementing compiler passes, IRs, and lowering pipelines for GPU kernel generation for DL compiler and framework integration. Building MLIR-based transformations and compiler infrastructure connecting frontend representations to backend code generation. Working within and contributing to the backend compilation stack itself, including tile-based IRs and their associated optimization and lowering infrastructure. Performance analysis and optimization across the codegen pipeline, targeting both compute-bound and memory-bound GPU kernels against competitive baselines. Making architectural decisions about how the codegen backend integrates with compiler frontends, GPU libraries, and NVIDIA's broader compilation ecosystem. Setting technical direction for your area: scoping multi-quarter work, defining abstractions that hold up as the stack evolves, and influencing roadmap priorities. Collaborating across teams, including hardware architects, framework teams, library teams, and external partners.

Requirements

• BS, MS, or PhD in Computer Science, Computer Engineering, or a related field (or equivalent experience).
• 6+ years of relevant work or research experience in compilers, with focus on code generation, IR design, or optimization passes.
• Strong C/C++ skills, including debugging, performance profiling, and designing for maintainability.
• Ability to work independently and drive projects with increasing scope and ambiguity.
• Strong interpersonal and communication skills, including the ability to work across teams and with external partners.

Nice To Haves

• Hands-on MLIR experience: designing dialects, writing passes, and reasoning about abstraction boundaries in a compilation pipeline.
• Track record of owning and delivering complex compiler infrastructure end to end.
• Working experience with GPU or other high-performance accelerator architectures and execution models.
• Contributions to open-source compiler projects (MLIR, LLVM, XLA, TVM, OAI Triton).
• History of mentoring engineers and raising the technical bar on a team.

Responsibilities

• Designing and implementing compiler passes, IRs, and lowering pipelines for GPU kernel generation for DL compiler and framework integration.
• Building MLIR-based transformations and compiler infrastructure connecting frontend representations to backend code generation.
• Working within and contributing to the backend compilation stack itself, including tile-based IRs and their associated optimization and lowering infrastructure.
• Performance analysis and optimization across the codegen pipeline, targeting both compute-bound and memory-bound GPU kernels against competitive baselines.
• Making architectural decisions about how the codegen backend integrates with compiler frontends, GPU libraries, and NVIDIA's broader compilation ecosystem.
• Setting technical direction for your area: scoping multi-quarter work, defining abstractions that hold up as the stack evolves, and influencing roadmap priorities.
• Collaborating across teams, including hardware architects, framework teams, library teams, and external partners.

Benefits

• With competitive salaries and a generous benefits package, we are widely considered to be one of the technology world’s most desirable employers.
• You will also be eligible for equity and benefits.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: Ph.D. or professional degree