Principal Software Engineer, d-Matrix

• MS or PhD preferred in Computer Science, Electrical Engineering, Math, Physics or related degree with 10-12+ Years of Industry Experience
• Strong grasp of computer architecture, data structures, system software, and machine learning fundamentals
• Experience with mapping NLP models (Transformers, State-Space Models, etc.) to accelerators and awareness of trade-offs across memory, BW and compute
• Proficient in Python/C/C++ development in Linux environment and using standard development tools
• Experience with deep learning frameworks (such as PyTorch, Tensorflow)
• Self-motivated team player with a strong sense of ownership and leadership

Desirable

• The role requires you to be part of the team that helps productize the SW stack for our AI compute engine. As part of the Software team, you will be responsible for the development, enhancement, and maintenance of the development and testing infrastructure for next-generation AI hardware.
• You can build and scale software deliverables in a tight development window. As a part of this team, you’ll be involved in leveraging the d-Matrix ISA and the dataflow architecture paradigm to build optimized implementations of SOTA large language models for achieving benchmark performance metrics.
• You will be involved in developing Machine Learning Op kernels for the graph-based d-Matrix compiler stack and with work with a team of compiler, hardware architecture experts, and Machine Learning model researchers during the process. You will also have the opportunity to contribute to the research of novel techniques for the Machine Learning software stack, models, and architecture