AI Research Engineer, Inference

Responsibilities

• Improve all aspects of large-scale model inference
• Develop GPU kernels using CUDA, Triton, Pallas, or CuTe DSL
• Work with novel inference devices including ASICs and FPGAs
• Manage data streaming and low-level PyTorch/JAX/XLA development
• Co-design and improve models in close collaboration with researchers

Requirements

• Two or more years of experience building deep learning systems
• Strong engineering skills in CUDA, Triton, Pallas, or CuTe DSL kernel development
• Experience with lower-level PyTorch, JAX, or XLA development
• Experience with CUDA Graphs or FPGA/ASIC hardware

Preferred Qualifications

• Experience translating methods between different areas of application
• Experience with Large Language Models (LLMs)

About the Company

Hudson River Trading (HRT) brings a scientific approach to trading financial products. We have built one of the world's most sophisticated computing environments for research and development, where researchers are at the forefront of innovation in algorithmic trading.