CUDA Engineering Expert at Mercor

CUDA Engineering Expert | $80–120/hr | Worldwide Remote

Mercor is seeking a skilled GPU kernel optimization expert to contribute to a high-impact project with a leading AI lab. This contract role is ideal for specialists who thrive on extracting maximum performance from modern GPU architectures using profiler-guided analysis and deep hardware knowledge.

Key Responsibilities

• Analyze and optimize GPU kernels for performance, efficiency, and hardware utilization
• Use profiler metrics — including L2 cache hit rate, L2 throughput, and occupancy — to guide kernel improvements
• Review GPU kernel implementations and identify performance bottlenecks
• Write, modify, and reason about C++17, Python, and GPU programming code
• Apply CUDA, HIP, shader programming, or related kernel expertise to improve performance outcomes
• Clearly document optimization decisions, including when specific profiler metrics are or are not applicable

Ideal Qualifications

• Available to work at least 20 hours per week
• Fluent in core C++ features through C++17
• Working knowledge of Python and Git
• Proficient in at least one GPU programming model: CUDA, HIP, Slang, HLSL, GLSL, or similar
• Minimum 1 year of professional or graduate-level GPU research experience
• Strong understanding of GPU profiler performance metrics and optimization strategies
• Ability to optimize kernels without requiring deep prior context on every algorithm

Bonus Qualifications

• Experience with CUDA C++ Core Libraries, inline PTX assembly, or tensor core-level optimization
• Experience optimizing kernels for NVIDIA Blackwell hardware
• Familiarity with NSight Compute
• Prior experience at GPU hardware organizations such as NVIDIA, AMD, or Qualcomm
• Open-source contributions related to GPU kernel optimization

Application Process

Submit your resume or relevant technical background to get started. Qualified applicants may be asked to complete a brief technical assessment or provide additional information.