Machine Learning Engineer — GPU Kernel

Mohamed bin Zayed University of Artificial Intelligence; Sunnyvale (CA); In loco; USD 150.000 - 450.000; Tempo pieno

Vantaggi offerti da questo lavoro

Medical, dental, vision benefits

Performance bonus

401K Plan

PTO and holidays

Parental Leave

Employee Assistance Program

Life insurance and disability

Descrizione del lavoro

MBZUAI seeks a GPU Kernel Engineer to optimize machine-learning software stacks, focusing on CUDA kernels and distributed training. You’ll profile, benchmark, and build tools to maximize GPU utilization on state-of-the-art platforms, collaborating with researchers and engineers.

The role emphasizes hands-on system-level coding, parallel computing, and involvement in design reviews to drive efficient, scalable deep learning systems.

Competenze

• Strong C++ and CUDA kernel development experience for deep-learning workloads.
• Understanding of GPU memory hierarchy and warp/block execution.
• Strong Python skills with PyTorch kernel integration and validation.

Mansioni

• Profile, optimize, and guide DL workloads on state-of-the-art hardware.
• Design benchmarks and testing methodologies for performance.
• Build tooling for workload analysis and optimization.
• Triage issues affecting GPU utilization and propose improvements.
• Develop kernels for new model architectures and algorithms.
• Lead design reviews and ensure code quality and documentation.

Conoscenze

C++ / CUDA kernel

GPU memory hierarchy

Python / PyTorch integration

Strumenti

Triton / CUTLASS / PTX

Distributed training systems

BF16 / FP8 precision

Descrizione del lavoro

About the Institute of Foundation Models

We are a dedicated research lab for building, understanding, using,and risk-managing foundation models. Our mandate is to advanceresearch, nurture the next generation of AI builders, and drivetransformative contributions to a knowledge-driven economy.

As part of our team, you’ll have the opportunity to work on thecore of cutting-edge foundation model training, alongsideworld-class researchers, data scientists, and engineers, tacklingthemost fundamental and impactful challenges in AIdevelopment.

You will participate in the development ofgroundbreaking AI solutions that have the potential to reshapeentire industries. Strategic and innovative problem-solving skillswill be instrumental in establishing MBZUAI as a global hub forhigh-performance computing in deep learning, driving impactfuldiscoveries that inspire the next generation of AI pioneers.

The Role

The GPU Kernel Engineer will play a role at the forefront ofoptimizing performance for the machine learning software stacks,especially at training and inference, and support the team todevelop new and cutting-edge systems. The ideal candidate will havea strong background in parallel computing, and hands-on experiencein system level coding, debug methodologies, and large-scalemachine learning experience.

This role focuses on CUDA kernel development and optimization.Distributed training experience is a plus.

Key Responsibilities

• Understand, analyze, profile, optimize, and provide guidance tothe team on deep learning workloads on state-of-the-art hardwareand software platforms to improve their efficiency with differentlevels of optimization
• Design and implement performance benchmarks and testingmethodologies to evaluate application performance
• Build tools to automate workload analysis, workloadoptimization, and other critical workflows
• Triage system issues and identify bottleneck and inefficienciesby analyzing the sources of issues and the impact on hardware,network and propose solutions to enhance GPU utilization
• Support the team to develop appropriate kernels and systems fornew model architectures and algorithms
• Participate in, or lead design reviews with peers andstakeholders to decide amongst available technologies.
• Review code developed by other developers and provide feedbackto ensure best practices (e.g., style guidelines, checking code in,accuracy, testability, and efficiency).
• Contribute to existing documentation or educational content andadapt content based on product/program updates and userfeedback.
• Represent MBZUAI at industry conferences and events, showcasingthe institution’s cutting-edge HPC and deep learning capabilitiesand establishing MBZUAI as a global leader in AI research andinnovation.
• Perform all other duties as reasonably directed by the linemanager that are commensurate with these functionalobjectives.
• Validate CUDA kernel outputs and gradients against referenceimplementations, and benchmark representative shapes, dtypes, andmodel workloads.

Technical Qualifications

Must-Haves:

• Strong C++ skills and hands-on CUDA kernel development andoptimization for deep-learning workloads.
• Understanding of GPU memory hierarchy, warp/block execution,and compute-memory trade-offs, with demonstrated profiling-drivenoptimization.
• Strong Python skills and experience integrating kernels withPyTorch or an equivalent framework, including numerical andgradient validation where needed.

Nice-to-Haves:

• Experience with Triton, CUTLASS, or PTX/SASS analysis.
• Experience with multi-node distributed training or inferencesystems.
• Experience validating mixed-precision computations, such asBF16 or FP8.

$150,000 - $450,000 a year

Compensation

$150,000 – $450,000/year + discretionary performance bonus +benefits

The posted salary range represents the company’s good faithestimate of the base compensation for this position upon hire. Theactual base compensation offered may vary within this rangedepending on individual qualifications, including but not limitedto relevant skills, experience, education, certifications, andspecific business needs. In addition to base salary, totalcompensation includes an annual discretionary performance bonus andcomprehensive benefits.

Benefits Include

• Comprehensive medical, dental, and vision benefits
• Bonus
• 401K Plan
• Generous paid time off, sick leave and holidays
• Paid Parental Leave
• Employee Assistance Program
• Life insurance and disability

We may use artificial intelligence (AI) tools to support parts ofthe hiring process, such as reviewing applications, analyzingresumes, or assessing responses and identifying potentialinconsistencies or verification signals in application materialsbased on available information. These tools assist our recruitmentteam but do not replace human judgment. Final hiring decisions areultimately made by humans. If you would like more information abouthow your data is processed, please contact us.