Senior Kernel Engineer: 26-02794

Job Description

\nPrimary Skills: CUDA programming (advanced), Triton optimization (advanced), Profiling tools (advanced), Debugging kernels (advanced), Performance tuning (advanced)\n
\nContract Type:  W2\n
\nDuration:  3+ months with possible extension or conversion\n
\nLocation: Bellevue, WA ()\n
\nPay Range: $85.00 - $90.00 Per hour on W2\n
\n#LP\n
\n
Job Summary: \n

This role involves the low-level development and optimization of compute kernels for AI accelerator hardware. You will ensure training environments accurately mirror real-world kernel engineering challenges by writing, debugging, and optimizing operators. A key aspect of this position is using profiling tools and accelerator programming interfaces to validate task realism and define solution quality.

Key Responsibilities: \n

\n
• Develop and optimize custom compute kernels for AI accelerators.
\n
• Validate training environment tasks for realistic kernel development scenarios.
\n
• Debug and profile kernel code to identify and resolve performance issues.
\n
• Analyze kernel performance against hardware constraints and memory hierarchy.
\n
• Consult with training environment development teams on task realism and quality.
\n

Must-Have Skills: \n

\n
• Computer Science, Computer Engineering, Electrical Engineering, or equivalent technical degree and 7+ years of relevant experience is required.
\n
• Direct experience with AWS Trainium/Inferentia and the Neuron Kernel Interface (NKI) and Hands-on proficiency with a low-level kernel programming language such as CUDA, Triton, or the AWS Neuron Kernel Interface (NKI).
\n
• Familiarity with the Neuron SDK, Neuron Profiler, and framework integration (PyTorch, JAX).
\n
• Experience porting kernels between accelerator backends (e.g., CUDA/Triton to NKI) and understanding of deep learning operator implementations (attention, GEMM, normalization).
\n

Industry Experience:
Experience in developing and optimizing low-level code for AI accelerators is essential, with a strong preference for experience with Triton over CUDA.\n
\n
ABOUT AKRAYA
Akraya is an award-winning IT staffing firm consistently recognized for our commitment to excellence and a thriving work environment .  Most recently, we were recognized Stevie Employer of the Year 2025, SIA Best Staffing Firm to work for 2025, Inc 5000 Best Workspaces in US (2025 & 2024) and Glassdoor's Best Places to Work (2023 & 2022)!

Industry Leaders in Tech Staffing
As Talent solutions provider for Fortune 100 Organizations, Akraya's industry recognitions solidify our leadership position in the IT staffing space.  We don't just connect you with great jobs, we connect you with a workplace that inspires!

Join Akraya Today!
Let us lead you to your dream career and experience the Akraya difference. Browse our open positions and join our team!\n