Senior AI Accelerator Architect — Training & Inference

QUALCOMM, Inc.; Folsom (CA); Presencial; USD 127 000 - 190 000; Tempo integral

Resumo da oferta

Qualcomm Technologies, Inc. is seeking an AI Accelerator Architecture Engineer to drive functional, performance and power enhancements in hardware for state-of-the-art AI training and inference across accelerators, servers, and SOCs.

You will work on flexible computational blocks, memory subsystems, NoC and scale-out architectures, and collaborate with software to define HW requirements and pre-silicon performance models.

Qualificações

• 3+ years hardware engineering experience defining architecture of GPUs or accelerators used for AI model training
• In-depth knowledge of Nvidia/AMD GPU capabilities and architectures
• Knowledge of LLM architectures and their HW requirements
• Master's or PhD in a related field is preferred

Responsabilidades

• Understand trends in ML network design from customer engagements and research and translate to SW/HW designs
• Collaborate with customers to determine hardware requirements for AI training systems
• Analyze current accelerator and GPU architectures
• Architect enhancements for efficient AI model training
• Design flexible computational blocks with various datatypes and precision

Conhecimentos

C++

Python

ML frameworks

Strong communication

Debugging skills

Learning agility

Formação académica

Master's degree in CS/Engineering

PhD in CS/Engineering

Bachelor's degree in CS/Engineering

Ferramentas

DeepSpeed

FSDP

TensorFlow

PyTorch

NVIDIA DGX

NVL72

Descrição da oferta de emprego

Qualcomm Technologies, Inc. is seeking an AI Accelerator Architecture Engineer to drive functional, performance and power enhancements in hardware for state-of-the-art AI training and inference across accelerators, servers, and SOCs.

You will work on flexible computational blocks, memory subsystems, NoC and scale-out architectures, and collaborate with software to define HW requirements and pre-silicon performance models.