Machine Learning Engineer - job 8 of 24

Job Summary

A company is looking for a Machine Learning Engineer to optimize inference performance for AI models on their platform.

Key Responsibilities

• Optimize inference performance for various AI models to minimize latency and maximize throughput
• Continuously experiment to achieve industry-leading performance on the platform
• Impact the performance of applications serving millions of users worldwide

Required Qualifications

• 1+ years of experience with state-of-the-art inference stacks (e.g., PyTorch, TensorRT, vLLM)
• Familiarity with modern AI workflows, including ComfyUI and LoRA adaptors
• Deep understanding of model compilation, quantization, and serving architectures
• Experience with GPU architectures and kernel-level optimizations
• Proficiency in programming with CUDA, Triton, or similar low-level accelerator frameworks