Nvidia is hiring a Senior Performance Compiler Engineer - Triton

About the Role

The role involves designing and optimizing compiler technologies that translate high-level operations into efficient machine code for specialized hardware, focusing on performance, scalability, and correctness.

Responsibilities

  • Develop and refine compiler passes to improve execution efficiency
  • Optimize code generation for domain-specific languages targeting accelerators
  • Collaborate with research and engineering teams to implement performance-critical features
  • Analyze and profile compiler output to identify bottlenecks
  • Ensure generated code meets hardware constraints and performance goals
  • Contribute to the architecture of a performance-oriented compiler stack
  • Debug and resolve issues in compilation pipelines
  • Implement transformations that reduce memory usage and latency
  • Work closely with hardware teams to align compiler output with architectural capabilities
  • Maintain and extend test infrastructure for compiler correctness
  • Document technical designs and implementation decisions
  • Support integration of compiler components into larger software ecosystems
  • Stay current with advancements in programming languages and compiler theory
  • Improve compilation speed without sacrificing output quality
  • Enable support for new language constructs and data types

Nice to Have

  • Experience with AI or machine learning frameworks
  • Contributions to open-source compiler projects
  • Familiarity with Triton or similar DSLs for tensor computation
  • Knowledge of CUDA or other GPU programming models
  • PhD in computer science or related discipline
  • Published work in programming languages or compiler design
  • Experience with formal verification in compiler contexts
  • Background in automatic parallelization techniques

Compensation

Competitive salary and benefits package

Work Arrangement

Hybrid work model available

Team

Part of the advanced compiler technologies group

About the Team

This team focuses on building next-generation compiler technologies that power AI acceleration. Members work at the intersection of software, algorithms, and hardware to deliver high-performance solutions.

Why This Role Matters

Efficient compilation is critical for unlocking the full potential of modern computing platforms. This role directly impacts how quickly and effectively AI models execute on hardware.

Visa sponsorship available for qualified candidates

Required Skills
C++CUDAPerformance OptimizationPython
About company
Nvidia
NVIDIA's invention of the GPU sparked the growth of the PC gaming market, redefined modern computer graphics, and revolutionized parallel computing for science and engineering. Today, the company is known as 'the AI computing company,' with the GPU acting as the brain of computers, robots, and self-driving cars that can perceive and understand the world.
All jobs at Nvidia Visit website
Job Details
Category other
Posted 10 months ago