onsite
Staff Software Engineer, Deep Learning Acceleration - Aurora Innovation
ML Engineer
Seeking a Staff Software Engineer to accelerate deep learning models. This role involves optimizing performance and developing cutting-edge solutions for self-driving technology.
About the role
Key Responsibilities
- Design and implement high-performance deep learning acceleration pipelines.
- Optimize machine learning models for efficiency and speed on various hardware platforms.
- Collaborate with research and engineering teams to integrate and deploy advanced AI capabilities.
- Develop and maintain robust software infrastructure for deep learning workloads.
- Troubleshoot and resolve performance bottlenecks in complex systems.
- Contribute to the architectural design of our deep learning stack.
Requirements
- Proven experience in deep learning model optimization and acceleration.
- Strong proficiency in Python and C++ for performance-critical applications.
- Experience with machine learning frameworks (e.g., TensorFlow, PyTorch).
- Familiarity with GPU computing and related technologies.
- Excellent problem-solving and debugging skills.
Skills
deep learningpythoncmachine learningperformance optimizationgpu computing