We are looking for dynamic and passionate engineers whose day-to-day work involves working on ML Frameworks such as PyTorch, Tensorflow, Jax etc.
The job role involves design and developing features in AI frameworks software stack.
You will be participated in enabling and optimizing state of the art deep learning models with a specific focus on the PyTorch framework.
In this role, you will work with a cross-geo team for delivering optimized software stack for Intel Gaudi (https://habana.ai/) Deep Learning accelerators.
The roles and responsibilities that you would need to performance may include the following:
� Design and develop SW techniques for AI frameworks - both HW-agnostic and HW-aware.
� Contribute to enhancing and extending the Training and Inference capabilities in the Software stack.
� Profile deep learning inference and training workloads and identify optimization opportunities in the software stack.
� BTech, MS or PhD in CS or related fields with an overall experience of 5 to 12 years.
� Must have: Proficient in Advanced C++ (C++ 14/17) and Intermediate skills of Python and parallel programming.
� Exposure to Machine Learning (ML) frameworks such as PyTorch and Tensorflow.
� Working knowledge of operators in Pytorch or Tensorflow and Understanding of low-level math kernels.
� Ability to debug complex issues in multi layered SW systems. Understanding of SW integration in large open-source framework and internal bridge layers.
� Understanding of computer architecture and HW-SW optimization techniques
� Practical knowledge of DL topologies for Vision / NLP / LLM will be a plus
� Experience working on frameworks/platforms that have gone to production.
� Knowledge of compiler algorithms for heterogeneous systems
� Effective communication skills and experience with working in a cross-geo setup.
Work Model for this Role
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.