Conducts design and development to build and optimize AI software. Designs, develops, and optimizes for AI frameworks (e.g., OpenVINO) and to contribute to external frameworks (e.g., TensorFlow, PyTorch).

Implements various distributed algorithms such as model/data parallel frameworks, parameter servers, dataflow based asynchronous data communication in machine learning, and/or deep learning frameworks.

Transforms computational graph representation of neural network model, and develops machine learning and/or deep learning primitives in mathematical libraries.

Profiles distributed deep learning models to identify performance bottlenecks and proposes solutions across individual component teams.

Optimizes code for various computing hardware backends, and interacts with machine learning and/or deep learning researchers, and utilizing experience with machine learning and/or deep learning frameworks.

Intel IOTG OpenVINO Runtime Engineering team is looking for a talented and highly motivated AI Frameworks Engineer.
Open VINO (https://github.com/openvinotoolkit/openvino) is an open-source toolkit for maximizing the performance of deep learning network models on various Intel platforms.

You will be working on developing highly-optimized software for Intel GPUs, collaborating with global Intel teams.

Your responsibilities will include, but not be limited to:

• Develop OpenVINO GPU plugin software based on Intel's integrated and discrete GPU architecture
• Analyze the performance of deep learning models on Intel GPUs and optimize GPU plugin to have the best performance for the models
• Develop primitives of deep learning models
• Develop new functionalities in GPU plugin with respect to business requirements
• Make GPU plugin to support future Intel GPU platforms

Qualifications

Required Qualifications

• Excellent programming and debugging skills with modern C++ on Linux (Experience on Windows is a plus)
• Strong computer science knowledge especially in programming languages, operating systems, and computer architecture for software performance analysis and optimization
• Willing to create effective software architecture and design
• Good communication skills for collaboration; Ability to conduct technical discussions in English (both written and verbal)
• Good problem-solving and trouble-shooting skills with a proactive mindset

Preferred Qualifications

• Programming experience on GPU or AI accelerator with parallel computing libraries
• Understanding of deep learning fundamentals and experience in deep learning frameworks
• Programming with Python or Shell script
• Experience with large-scale software projects, working with cross-geo teams

Additional Notes:

• We are looking for both junior and senior engineers.
• -In this role, you will work in a hybrid working model (onsite + working from home). You will be working from home, but you will be present on-site on demand.

The Network & Edge Group brings together our network connectivity and edge into a business unit chartered to drive technology end to end product leadership. It's leadership Ethernet, Switch, IPU, Photonics, Network and Edge portfolio is comprised of leadership products critically important to our customers.