OpenVINO AI Frameworks engineer

Job Details:

Job Description: 

Join Intel's OpenVINO team, a critical force in accelerating AI inference from the edge to the cloud. Our mission is to empower developers worldwide by optimizing deep learning models for maximum performance across diverse Intel hardware. You'll be an integral part of the OpenVINO Conversion team, specifically focusing on the trending OpenVINO GenAI, which is at the forefront of enabling efficient and powerful Generative AI pipelines deployments.

As OpenVINO AI Frameworks engineer on the OpenVINO Conversion team, you will spearhead the development and enhancement of innovative use cases for the OpenVINO GenAI. This exciting role involves diving deep into the architecture of generative models and OpenVINO, implementing new features, and optimizing performance to deliver state-of-the-art inference solutions.

Key Responsibilities:

• Develop, and implement new features and enhancements for the OpenVINO GenAI, focusing on expanding API coverage for diverse generative AI models (e.g., LLMs, Diffusion models, Multimodal models).
• Optimize the performance and efficiency of generative AI model inference within the OpenVINO framework, leveraging advanced techniques like speculative decoding and KV Cache optimization.
• Analyze and integrate cutting-edge research in generative AI, translating advancements into practical OpenVINO GenAI capabilities.
• Collaborate closely with AI researchers, other engineering teams, and product managers to understand requirements and deliver robust solutions.
• Participate in code reviews, contribute to technical documentation, and ensure high code quality and maintainability.
• Debug and troubleshoot complex issues related to model conversion and inference performance in OpenVINO GenAI.

Qualifications:

Required Qualifications:

• Bachelor’s, Master’s Computer Science, Computer Engineering, Mathematics, or a related field.
• Experience with Deep Learning and Neural Network architectures, particularly Generative AI models (e.g., Transformers, Diffusion models).
• Familiarity with popular AI frameworks such as PyTorch, TensorFlow, and the Hugging Face Transformers library.
• Minimum of 5 years of hands-on development experience utilizing C/C++, Python.
• Demonstrated understanding of multithreading concepts and practical experience in developing the thread-safe code
• Strategic problem-solver: You possess the ability to dissect challenging technical problems and devise practical solutions that align with project goals and constraints.
• Impactful communicator & cross-functional collaborator: You excel at conveying technical insights clearly and building strong partnerships, thriving in both independent work and collaborative environments.
• Effective verbal and written communication skills in English (intermediate level or higher).

Preferred Qualifications (A Plus):

• Experience with model optimization techniques (i.e., quantization, pruning).
• Knowledge of the OpenVINO Toolkit or other deep learning inference runtimes(ONNX Runtime, Lite RT, Executorch).
• Experience contributing to open-source projects.

          

Job Type:Experienced Hire

Shift:Shift 1 (United Arab Emirates)

Primary Location: United Arab Emirates, Dubai

Additional Locations:

Business group:The Client Computing Group (CCG) is responsible for driving business strategy and product development for Intel's PC products and platforms, spanning form factors such as notebooks, desktops, 2 in 1s, all in ones. Working with our partners across the industry, we intend to deliver purposeful computing experiences that unlock people's potential - allowing each person use our products to focus, create and connect in ways that matter most to them. As the largest business unit at Intel, CCG is investing more heavily in the PC, ramping its capabilities even more aggressively, and designing the PC experience even more deliberately, including delivering a predictable cadence of leadership products. As a result, we are able to fuel innovation across Intel, providing an important source of IP and scale, as well as help the company deliver on its purpose of enriching the lives of every person on earth.

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 TrustN/A

Work Model for this Role

This role will require an on-site presence. * Job posting details (such as work model, location or time type) are subject to change.