CUDA Kernel Optimizer - ML Engineer

• Role Overview
  
  
  

Mercor is engaging advanced CUDA experts who specialize in GPU kernel optimization, performance profiling, and numerical efficiency. These professionals possess a deep mental model of how modern GPU architectures execute deep learning workloads. They are comfortable translating algorithmic concepts into finely tuned kernels that maximize throughput while maintaining correctness and reproducibility,

• Key Responsibilities
• Develop, tune, and benchmark CUDA kernels for tensor and operator workloads.
• Optimize for occupancy, memory coalescing, instruction-level parallelism, and warp scheduling.
• Profile and diagnose performance bottlenecks using Nsight Systems, Nsight Compute, and comparable tools.
• Report performance metrics, analyze speedups, and propose architectural improvements.
• Collaborate asynchronously with PyTorch Operator Specialists to integrate kernels into production frameworks.
• Produce well-documented, reproducible benchmarks and performance write-ups.
• Ideal Qualifications
• Deep expertise in CUDA programming, GPU architecture, and memory optimization.
• Proven ability to achieve quantifiable performance improvements across hardware generations.
• Proficiency with mixed precision, Tensor Core usage, and low-level numerical stability considerations.
• Familiarity with frameworks like PyTorch, TensorFlow, or Triton (not required but beneficial).
• Strong communication skills and independent problem-solving ability.
• Demonstrated open-source, research, or performance benchmarking contributions.
• More About the Opportunity
• Ideal for independent contractors who thrive in performance-critical, systems-level work.
• Engagements focus on measurable, high-impact kernel optimizations and scalability studies.
• Work is fully remote and asynchronous; deliverables are outcome-driven.
• Access to shared benchmarking infrastructure and reproducibility tooling via Mercor support resources.
• Compensation & Contract Terms
• Typical range: $120–$250/hour, depending on scope, specialization, and results achieved. Payments will be based on accepted task output over flat hourly.
• Structured as a contract-based engagement, not an employment relationship.
• Compensation tied to measurable deliverables or agreed milestones.
• Confidentiality, IP, and NDA terms as defined per engagement.
• Application Process
• Submit a brief overview of prior CUDA optimization experience, profiling results, or performance reports.
• Include links to relevant GitHub repos, papers, or benchmarks if available.
• Indicate your hourly rate, time availability, and preferred engagement length.
• Selected experts may complete a small, paid pilot kernel optimization project
• About Mercor
• Mercor connects domain experts with top AI research and technology organizations through project-based contracts.
• Contractors operate independently, with full flexibility over methods, timelines, and tools.
• Our mission is to help top engineers and researchers access frontier technical work without rigid employment structures.