Machine Learning Engineer — GPU Kernel
$150k - $450k • Sunnyvale, CA • Full-time
Posted 12d ago
Job Location
Sunnyvale, CA
Tech Stack
Remote Work Policy
On-site
Employment Type
Full-time
Categories
Machine Learning Engineer
About the job
We are a dedicated research lab focused on building, understanding, using, and risk-managing foundation models. Our mission is to advance research, nurture the next generation of AI builders, and drive transformative contributions to a knowledge-driven economy. As part of our team, you will work on the core of cutting-edge foundation model training alongside world-class researchers, data scientists, and engineers. You will tackle fundamental and impactful challenges in AI development, contributing to groundbreaking AI solutions that have the potential to reshape entire industries. Strategic and innovative problem-solving skills are essential for establishing our institution as a global hub for high-performance computing in deep learning.
Responsibilities
- Understand, analyze, profile, and optimize deep learning workloads on state-of-the-art hardware and software platforms to improve efficiency.
- Design and implement performance benchmarks and testing methodologies to evaluate application performance.
- Build tools to automate workload analysis, optimization, and other critical workflows.
- Triage system issues, identify bottlenecks and inefficiencies, and propose solutions to enhance GPU utilization.
- Support the development of appropriate kernels and systems for new model architectures and algorithms.
- Participate in or lead design reviews with peers and stakeholders to decide amongst available technologies.
- Review code developed by other developers and provide feedback to ensure best practices.
- Contribute to existing documentation or educational content and adapt it based on product/program updates and user feedback.
- Represent the institution at industry conferences and events, showcasing its HPC and deep learning capabilities.
- Validate CUDA kernel outputs and gradients against reference implementations, and benchmark representative shapes, dtypes, and model workloads.
Requirements
- Strong C++ skills and hands-on CUDA kernel development and optimization for deep-learning workloads.
- Understanding of GPU memory hierarchy, warp/block execution, and compute-memory trade-offs, with demonstrated profiling-driven optimization.
- Strong Python skills and experience integrating kernels with PyTorch or an equivalent framework, including numerical and gradient validation.
- Experience with Triton, CUTLASS, or PTX/SASS analysis (nice-to-have).
- Experience with multi-node distributed training or inference systems (nice-to-have).
- Experience validating mixed-precision computations, such as BF16 or FP8 (nice-to-have).