Hybrid AI Model Optimization Engineer

Intel Corporation; George Town; Híbrido; MYR 120.000 - 180.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Hybrid work model

Descripción de la vacante

Intel Corporation in Malaysia, Penang, seeks an AI Model Optimization Engineer to deliver optimized AI models for Intel products and enable adoption by partners and customers. You will develop, test, and debug software that makes AI models run fast and accurately on Intel hardware.

The role involves benchmarking, hardware-aware optimization, and collaboration across teams within Client Computing and PhysicalAI Group. Hybrid work model in Penang is available.

Formación

• Bachelor's or Master's in a relevant field with hands-on AI experience.
• Proficiency in Python and C++ programming.
• Experience with PyTorch or TensorFlow.
• Knowledge of Git-based workflows.
• Familiarity with AI hardware optimization concepts.

Responsabilidades

• Enable and validate AI models on Intel GPUs.
• Optimize AI model performance focusing on speed and accuracy.
• Implement benchmarks and analyze results.
• Triage and debug issues across framework/runtime layers; escalate with evidence.
• Contribute upstream pull requests and document code and tests.

Conocimientos

Python

C++

PyTorch

TensorFlow

Git

GenAI

AI frameworks

Educación

Bachelor's degree in a relevant field

Master's degree in a relevant field

Herramientas

OpenVINO

Descripción del empleo

Intel Corporation in Malaysia, Penang, seeks an AI Model Optimization Engineer to deliver optimized AI models for Intel products and enable adoption by partners and customers. You will develop, test, and debug software that makes AI models run fast and accurately on Intel hardware.

The role involves benchmarking, hardware-aware optimization, and collaboration across teams within Client Computing and PhysicalAI Group. Hybrid work model in Penang is available.