AI Inference Engineer — Large-Scale Models & Hardware

Wehrtyou; Greater London; Presencial; GBP 188.000 - 225.000; Jornada completa

Descripción de la vacante

Hudson River Trading (HRT) seeks an AI Research Engineer (Inference) to join the HAIL team. The role focuses on large-scale model inference, GPU kernel development, and novel accelerator devices to support market-focused foundation models.

You will work closely with researchers to co-design and advance inference capabilities, deploying diverse solutions across global data centers and driving measurable impact on trading performance.

Formación

• Strong engineering skills in GPU/AI tooling and kernels.
• 2+ years building deep learning systems across domains.
• Experience translating methods between areas of application is valued.
• LLM experience is useful but not required.

Responsabilidades

• Improve large-scale model inference and performance.
• Develop GPU kernels, FPGA/ASIC inference devices, and streaming data paths.
• Collaborate with researchers to co-design models and shape research agenda.

Conocimientos

CUDA kernel development

PyTorch/JAX basics

FPGA/ASIC experience

Deep learning systems

Model inference optimization

LLM experience

Herramientas

CUDA Graphs

CuTe DSL

Pallas

Triton

Descripción del empleo

Hudson River Trading (HRT) seeks an AI Research Engineer (Inference) to join the HAIL team. The role focuses on large-scale model inference, GPU kernel development, and novel accelerator devices to support market-focused foundation models.

You will work closely with researchers to co-design and advance inference capabilities, deploying diverse solutions across global data centers and driving measurable impact on trading performance.