LLVM Compiler Optimization Engineer for Intel AI Accelerator

Job Description

• 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.

Additional:

• Designs and develops LLVM IR transformation passes to optimize deep learning primitives for various cutting-edge AI Frameworks targeted for Intel's accelerators.
• 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.

#ijireland

Qualifications

Minimum qualifications are required to be initially considered for this position. Preferred qualifications are in addition to the minimum requirements and are considered a plus factor in identifying top candidates.

Minimum Qualifications:

• Masters in Computer Science or equivalent
• At least 3-5 years of experience with compiler frameworks, design and implementation of IR optimizations in C/C++
• Experience with development of LLVM transformation passes
• Good understanding of graph based algorithms
• Good system-level debugging skills
• Knowledge of common machine learning frameworks will be beneficial
• Strong production software engineering background, experience with CI, code reviews, paired programming, unit and integration testing

Requirements listed would be obtained through a combination of industry relevant job experience, internship experiences and or schoolwork/classes/research.

Inside this 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.

Benefits

We offer a total compensation package that ranks among the best in the industry. It consists of competitive pay, stock, bonuses, as well as, benefit programs which include health, retirement, and vacation. Find more information about all of our Amazing Benefits here.

Working Model

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. In certain circumstances the work model may change to accommodate business needs.