Responsibilities
- Design and build optimizations in graph compilers to boost AI model performance, lower latency, and improve hardware usage.
- Collaborate with machine learning researchers, hardware engineers, and software teams to deploy models and solve hardware-specific implementation challenges.
- Optimize neural network performance through techniques such as layer fusion, operator fusion, and graph restructuring.
- Create compiler passes that transform high-level AI models from frameworks like TensorFlow and PyTorch into intermediate representations.
- Build components for parsing, semantic validation, and intermediate representation generation in deep learning compilers.
- Investigate and apply cutting-edge research in compiler technology, model optimization, and hardware acceleration to improve graph compiler capabilities.
- Lead, mentor, and guide engineers working on compiler optimization projects, providing technical direction and support.
Other
This company provides equal employment opportunities to all applicants in the United States.
