OpenVINO AI Frameworks engineer

Job Details:

Job Description: 

Join Intel's pioneering OpenVINO team, a critical force in accelerating AI inference from the edge to the cloud. Our mission is to empower developers worldwide by optimising deep learning models for maximum performance across diverse Intel hardware.

You'll be an integral part of the OpenVINO Conversion team, focusing on the crucial task of converting AI models from various popular frameworks into the optimised OpenVINO Intermediate Representation (IR).

As an OpenVINO AI Frameworks Engineer on the Model Conversion team, you will be directly responsible for the conversion of deep learning models from their original framework formats (such as PyTorch, TensorFlow, ONNX) into the OpenVINO IR. This foundational role involves deep dives into model architectures, framework specifics, and OpenVINO's internal representation to ensure seamless, accurate, and performant model compatibility.

Key Responsibilities:

• Develop and enhance model conversion pipelines and tools within OpenVINO to support new deep learning models and operations from various AI frameworks (e.g., PyTorch, TensorFlow, Keras3, ONNX, JAX/Flax).
• Analyse and address complex conversion challenges, including unsupported operations, graph transformations, and data type compatibility issues, ensuring accurate representation in the OpenVINO IR.
• Implement and optimise graph passes and transformations within the OpenVINO Model Converter to improve model efficiency and readiness for inference.
• Collaborate closely with runtime engineers and research teams to stay abreast of model advancements and ensure broad OpenVINO compatibility.
• Contribute to comprehensive technical documentation and user guides for model conversion processes and best practices.
• Participate in code reviews and uphold high standards for code quality, test coverage, and maintainability.
• Debug and troubleshoot conversion failures and discrepancies, providing robust solutions and workarounds

Qualifications:

Minimum Qualifications:

• Bachelor’s or Master’s degree in Computer Science, Computer Engineering, Mathematics, or a related field.
• Minimum of 5 years of hands-on development experience utilising C/C++ and Python.
• Strong understanding of Deep Learning concepts, neural network architectures, and common operations (e.g., convolution, pooling, attention).
• Demonstrated experience with at least two major AI frameworks (e.g., PyTorch, TensorFlow, ONNX), including their graph representations and execution models.
• 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).

Nice to have:

• Knowledge of compiler design principles or graph optimisation techniques.
• Familiarity with Generative AI models (e.g., LLMs, Diffusion models) and their unique conversion challenges.
• Experience with model optimisation techniques (e.g., quantisation, pruning, graph fusion).
• Knowledge of the OpenVINO Toolkit or other deep learning inference runtimes(ONNX Runtime).
• Experience contributing to open-source projects.

What We Offer? 

At Intel, employees share in successes, enjoy comprehensive rewards and are inspired by an innovative & inclusive workplace. What can you expect when there is a match between us?

• We guarantee you will be working in a safe environment - either at your own home or in our premises if needed, the security and wellbeing of you and your family stands as our utmost responsibility.

• You will have constant opportunities to develop your professional career through technical and soft skills training, taking part in innovation projects or rotational programs

• Flexible working hours are important to us

• Our Amazing Benefits to make life easier and more enjoyable are waiting for you: Stock Program, Annual and Quarterly Bonuses, Employee Pension Plan, Medical Plan and life insurance for you and your Family, Peer to peer recognition, Ticket restaurant Card, Multisport Card / Holiday card, Groups of enthusiasts, Exclusive employee discounts, (online) events and many more.

• Rewards Experience @ Intel Poland: https://jobs.intel.com/pl/benefits

* Job posting details (such as work model, location or time type) are subject to change.

          

Job Type:

Experienced Hire

Shift:

Shift 1 (Poland)

Primary Location: 

Poland, Gdansk

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 Trust

N/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.