Machine Learning Engineer - Kernels

Mindbeam AI

Job Overview

Location

United States

Job Type

Full-time

Full Job Description

📋 Description

• Design and implement custom GPU and accelerator kernels to maximize performance for next-generation AI workloads.
• Profile, benchmark, and optimize critical machine learning workloads to achieve peak computational efficiency.
• Collaborate directly with research teams to translate cutting-edge algorithmic innovations into efficient, production-ready low-level code.
• Stay current with advancements in hardware technologies including CUDA, ROCm, and TPU architectures to inform kernel design decisions.
• Develop and document best practices for low-level optimization to ensure knowledge sharing across engineering and research teams.
• Optimize machine learning workloads for distributed and heterogeneous compute environments, including multi-GPU and multi-node systems.
• Use performance profiling and diagnostics tools to identify bottlenecks and drive targeted improvements in kernel execution.
• Work at the intersection of machine learning algorithms and hardware architecture to bridge theoretical advancements with practical deployment.
• Contribute to the development of open-source AI infrastructure by creating high-performance, reusable kernel components.
• Ensure code quality through rigorous testing, version control, and adherence to performance benchmarks in production environments.
• Communicate technical trade-offs and optimization strategies clearly to both engineering and research stakeholders.
• Participate in code reviews and technical discussions focused on performance, scalability, and hardware utilization.
• Investigate emerging accelerator technologies and evaluate their applicability to current and future AI workloads.
• Maintain a performance-obsessed mindset, relentlessly pursuing efficiency gains in memory bandwidth, compute throughput, and latency reduction.
• Translate complex mathematical operations from ML frameworks into optimized low-level implementations that leverage hardware-specific features.
• Contribute to the evolution of Mindbeam’s AI infrastructure by proposing and implementing novel kernel-level optimizations.

🎯 Requirements

• Bachelor’s, Master’s, or PhD in Computer Science, Electrical Engineering, or related field—or equivalent experience
• 2+ years of experience in GPU programming, parallel computing, or systems-level optimization
• Strong coding skills in C++, CUDA, or similar languages
• Familiarity with ML frameworks and their low-level backends
• Experience optimizing workloads for distributed and heterogeneous compute environments
• Comfort with profiling tools and performance diagnostics

🏖️ Benefits

• Opportunity to work on cutting-edge AI infrastructure with a research-oriented team
• Collaborative environment where bold ideas and performance-driven innovation are encouraged
• Exposure to state-of-the-art hardware technologies including CUDA, ROCm, and TPU
• Direct impact on open-source AI development and industry-wide performance standards

Skills & Technologies

Onsite

Degree Required

Ready to Apply?

Apply Externally

You will be redirected to an external site to apply.

AI Job Fit Analysis

Pro

See exactly how your profile matches this role — strengths, skill gaps, and what to do about them.

Mindbeam AI

Visit Website

About Mindbeam AI

Mindbeam AI is a New York City–based startup specializing in next-generation AI infrastructure. Its flagship product, Litespark, is a framework designed to accelerate the pre-training and fine-tuning of large language models (LLMs). Litespark utilizes advanced algorithms to significantly reduce training times—from months to days—while minimizing costs and energy consumption. The framework is compatible with industry-standard machine learning frameworks like PyTorch, TensorFlow, and JAX, and is optimized for NVIDIA GPU hardware. Mindbeam's solutions are utilized by Fortune 100 enterprises and are available on AWS Marketplace.

View Company Profile

Get more remote jobs like this

Subscribe to the weekly newsletter for similar remote roles and curated hiring updates.

Weekly remote jobs and featured talent.

No spam. Only curated remote roles and product updates. You can unsubscribe anytime.