AI Model Optimization Engineer

About the Role

Intel is seeking an AI Model Performance Optimization Engineer to deliver high-performance AI solutions for next-generation client computing experiences. This role involves enabling, validating, benchmarking, optimizing, and debugging AI models to ensure efficient and accurate execution on Intel hardware platforms. You will work at the intersection of artificial intelligence, machine learning frameworks, software engineering, and hardware acceleration, collaborating with engineers across Intel to improve AI model performance, scalability, and adoption by customers and partners globally. This is an opportunity for engineers passionate about Generative AI, machine learning systems, model optimization, and performance engineering.

Key Responsibilities

• Enable, validate, benchmark, and optimize AI models on Intel platforms to address customer and market segment needs.
• Analyze model performance and identify optimization opportunities.
• Debug issues across AI frameworks, software stacks, and hardware platforms.
• Develop and execute tests to ensure model functionality, accuracy, and performance.
• Collaborate with software, hardware, compiler, and architecture teams to solve technical challenges.
• Utilize AI-assisted development tools to improve engineering productivity.
• Contribute code, bug fixes, documentation, and test coverage to internal and open-source projects.
• Work effectively with globally distributed engineering teams.
• Mentor junior engineers and share technical expertise.

Qualifications

Minimum Qualifications

• Bachelor's degree in Computer Science, Computer Engineering, Electrical Engineering, Artificial Intelligence, Machine Learning, or a related technical discipline with 3+ years of hands-on experience in AI frameworks, algorithms, and programming.
• OR Master's degree in the same field with 2+ years of experience.
• Programming in Python and/or C++.
• Experience with machine learning or deep learning frameworks such as PyTorch or TensorFlow.
• Performance analysis, profiling, and optimization.
• Working knowledge of Git-based collaborative development and pull-request workflows.
• Basic understanding of computer architecture and operating systems.

Preferred Qualifications

• Linux and/or Windows operating systems.
• Experience with GenAI models (LLM, VLM, VLA) or OpenVINO.
• Understanding of parallel programming, preferably with experience in SYCL or OpenCL.
• Previous publications or contributions to AI research.
• Familiarity with OpenVINO or other AI inference frameworks.
• Experience contributing to open-source software projects.