We are looking for a dynamic software engineer to design, develop and optimize AI frameworks for training and inference on Intel Habana (https://habana.ai/) deep learning accelerators. In this role, you will work with a cross-geo team on enabling and optimizing state of the art deep learning models with a specific focus on the PyTorch framework. The roles and responsibilities that you would need to carry out may include the following:
� Profile and enable deep learning inference and training workloads on Habana DL accelerators. Debug /fix functional and convergence issues, identify performance optimization opportunities and drive implementation of these optimizations.
� Design and develop SW techniques for AI frameworks - both HW-agnostic and HW-aware.
� Contribute to enhancing and extending the Training and Inference capabilities of DL accelerator Software stack.
Qualifications
� BTech, MS or PhD in CS or related fields with an overall experience of 3-10 years.
� Programming skills in Python, C++, and parallel programming skills.
� Previous exposure to Deep Learning (DL) frameworks such as PyTorch, Tensorflow, JAX.
� Familiarity with Generative AI models and LLMs.
� Exposure to working on open-source DL projects.
� Working knowledge of operators in Pytorch/Tensorflow and Understanding of low-level kernels.
� Understanding of computer architecture and HW-SW optimization techniques.
� Experience working on frameworks/platforms that have gone to production.
� 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.