Intel · posted · checked
AI Model Optimization Engineer
C++PythonPytorchTensorflowHybrid · MalaysiaMid-level
Who can apply
Hybrid · Malaysia
Location: Malaysia, Penang
Job Details:
Job Description:
The Role and Impact
As an AI Model Optimization Engineer, you will play a pivotal role in delivering optimized AI Models for Intel products, driving their adoption among partners and customers.
You will develop, test, and debug the software that makes AI models run fast and accurately on Intel hardware.
By leveraging your expertise in AI frameworks, algorithms, and hardware, you will contribute to developing cutting-edge technology that optimizes AI Models.
Business Group
This role is part of Intel Corporation's diverse and innovative workforce within the Client Computing and PhysicalAI Group. The team collaborates across engineering and product development domains to design and optimize solutions that advance Intel's leadership in Client and PhysicalAI Technologies. Focused on enabling technology adoption and delivering performance-driven AI solutions, the team contributes to Intel's broader mission of powering progress and innovation worldwide.
Key Responsibilities
Enable and validate AI models on Intel GPUs to address customer and market segment needs.
Optimize the performance of AI Models, focusing on performance and accuracy using Intel Hardware features.
Implement and run benchmarks to measure model performance; analyse and report results.
Triage and debug issues across the framework and runtime layers, isolating driver-level defects and escalating them with supporting evidence.
Use AI-agent-assisted workflows to accelerate debugging and model enablement.
Show the full posting
Contribute upstream pull requests - bug fixes, test coverage, and documentation.
Document code, test and procedures to ensure clarity and maintainability.
Qualifications:
Minimal Qualifications: