AI Compiler Developer - Waterford Office

Introduction
As a developer on the AI on IBM Z team you bring AI and machine learning capabilities to IBM’s flagship enterprise server – IBM Z. This includes providing the capabilities for customers to train deploy inference and monitor AI/ML models on z/OS and empowers transactions and applications on IBM Z to infuse trustworthy AI at scale without impacting service level agreements (performance).
The AI on IBM Z development team is driving the product development and delivery lifecycle with continuous delivery approach and agile practices including roadmap design development testing delivery and technical support of the product. The AI on IBM Z development team is a global team with talent based in multiple countries. Now we’re looking for additional developers to strengthen the capacity of the team and work together to better execute our product roadmap.

Your Role and Responsibilities
In this job offering we are specifically looking for new team members to grow our Deep Learning & Compiler teams in the AI Group. If you’re a motivated and talented individual who is passionate about deep learning and compiler development we want you.
As a Deep Learning Compiler Developer you will be responsible for designing developing and optimizing deep learning models and compiler infrastructure to accelerate AI workloads. You will work closely with our research team to develop novel compiler techniques and integrate them with deep learning frameworks.
As a Compiler Technology Developer for the IBM Z Deep Learning Compiler on IBM Z AI and Analytics team you will be responsible for development maintenance test and delivery of deep learning compiler-related technologies. You will work together with the IBM Z team the IBM Research team and more on technologies such as LLVM and ONNX-MLIR to optimize use of the AI capabilities on IBM Z.
Additional Responsibilities:
Design and develop novel compiler techniques to optimize deep learning models for various hardware platforms.
Collaborate with research team to develop and integrate new deep learning algorithms and models.
Optimize and fine-tune deep learning models for performance power and memory efficiency.
Develop and maintain compiler infrastructure to support various deep learning frameworks (e.g. TensorFlow PyTorch).
Work with cross-functional teams to integrate compiler optimizations with other components of the AI stack.
Develop and maintain technical documentation and testing frameworks.
Stay up-to-date with the latest advancements in deep learning and compiler research.
***PLEASE NOTE*** – This position is based in our Waterford location and requires working onsite 3 days per week.

Required Technical and Professional Expertise

• Familiarity with a variety of software engineering concepts including practices and procedures related to open source technologies.
• General software development test and/or debug skills.
• Demonstrated experience and usage of one or more programming languages such as C C++ Python Scala Or Java.
• Knowledgeable on software engineering best practices (code reviews).
• Knowledge of computer architecture parallel processing and optimization techniques.

Preferred Technical and Professional Expertise

• Compiler design principles.
• Experience with Machine Learning frameworks (e.g. Pytorch) and Machine Learning Models.
• Proficient in source control management tools (e.g GitHub and Jenkins).
• Familiarity with Data Science.
• Familiarity with the IBM LinuxOne and/or IBM Z systems.