AI Model Optimization Engineer

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. • Contribute upstream pull requests - bug fixes, test coverage, and documentation. • Document code, test and procedures to ensure clarity and maintainability. Qualifications: Minimal Qualifications: • Bachelor's degree in a relevant field with 3+ years of hands-on experience in AI frameworks, algorithms, and programming OR Master's degree in a relevant field with 2+ years of experience • Solid understanding of software development principles and programming skills in Python and C++. • Familiarity with at least one deep learning framework (e.g., PyTorch, TensorFlow). • Basic understanding of computer architecture and operating systems. • Working knowledge of Git-based collaborative development and pull-request workflows. • Strong problem-solving skills and a willingness to learn. Preferred Qualifications : • Experience with GenAI models (LLM, VLM, VLA) or OpenVINO. • Result orientation and strong ability to collaborate across teams. • Previous publications or contributions to AI research. • Familiarity with OpenVINO or other model optimization toolkits. Your expertise will not only contribute to the success of Intel's products but also shape the future of AI innovation. Join us to work on impactful projects and drive meaningful advancements in the industry. Job Type: Experienced Hire Shift: Shift 1 (Malaysia) Primary Location: Malaysia, Penang Additional Locations: Posting Statement: All qualified applicants will receive consideration for employment without regard to race, color, religion, religious creed, sex, national origin, ancestry, age, physical or mental disability, medical condition, genetic information, military and veteran status, marital status, pregnancy, gender, gender expression, gender identity, sexual orientation, or any other characteristic protected by local law, regulation, or ordinance. Position of Trust N/A Work Model for this Role This role will be eligible for our hybrid work model which allows employees to split their time between working on-site at their assigned Intel site and off-site. * Job posting details (such as work model, location or time type) are subject to change. * ADDITIONAL INFORMATION: Intel is committed to Responsible Business Alliance (RBA) compliance and ethical hiring practices. We do not charge any fees during our hiring process. Candidates should never be required to pay recruitment fees, medical examination fees, or any other charges as a condition of employment. If you are asked to pay any fees during our hiring process, please report this immediately to your recruiter.