LLM Inference Kernel Engineer

Job Summary

A company is looking for a LLM Inference Kernel Engineer MLA.

Key Responsibilities

• Design and implement high-performance GPU kernels for large language model inference workloads
• Optimize CUDA kernels focusing on memory efficiency, execution speed, and latency reduction
• Collaborate on integrating optimized kernels into modern inference serving frameworks

Required Qualifications

• Strong experience developing GPU kernels using CUDA C or C++ in performance-critical environments
• Hands-on experience optimizing inference workloads for large language models
• Solid understanding of attention mechanisms and advanced implementations
• Deep knowledge of GPU architecture, including memory hierarchy and latency tradeoffs
• Ability to operate in a fast-paced, highly iterative environment with minimal oversight