Responsibilities and Opportunities
- Conduct performance analysis of large-scale systems built using our Rebellions' NPU
- Conduct performance analysis of models on competitor hardware/systems
- Contribute to driving features into our hardware based on workload optimizations/insight
Key Qualifications
- Minimum of 4 years of experience in software engineering
- Master’s or higher degree in Computer Science, Electrical Engineering, or related field
- Experience with analyzing, profiling, and optimizing large language model inference on GPU/NPU
- Experience with processor and system-level performance modelling
- Understanding of processor architectures and distributed systems and their implications on ML model performance
- Proficiency with C/C++ and Python
- Experience with TensorFlow, Pytorch, or other ML frameworks
Ideal Qaulifications
- Effective communication and presentation skills
- Able to work in a very dynamic startup environment