Inference Optimization Engineer

What you'll do

• Profile model architectures and workloads to identify performance bottlenecks and measure optimization results.
• Develop inference optimizations, including algorithmic improvements and GPU kernels, across single-GPU, multi-GPU, and multi-node systems.
• Build benchmarking and profiling infrastructure, evaluate runtimes and hardware, and help deploy research models efficiently at scale.

What they ask for

• Deep technical ability in efficient ML inference, ML systems, GPU computing, or adjacent research, demonstrated through relevant work.
• Strong understanding of deep learning execution on hardware, including compute, memory, communication, and performance.
• Experience profiling ML workloads, identifying bottlenecks, and delivering measurable performance improvements.
• Strong programming fundamentals in Python, C++, or another systems-oriented language; experience with some combination of PyTorch, CUDA, Triton, TensorRT, vLLM, SGLang, or comparable technologies.

Nice to have

• Experience optimizing large generative, multimodal, vision, or video models.
• GPU kernel development, GPU architecture, inference optimization, model compilation, or multi-GPU/multi-node execution experience.

Tools

Python, C++, PyTorch, CUDA, Triton, TensorRT, vLLM, SGLang

AI focus

Optimizes inference for visual and multimodal models, helping turn research advances into models that can be served efficiently at scale.