Software Engineer, Perception
- Pittsburgh, PA
- $146,000-234,000 per year
- Permanent
- Full-time
- Collaborate with other members of the Perception autonomy team to improve/ideate and implement perception algorithms that power the Aurora Driver
- Serve as a technical expert for the team on at least one area related to machine learning, with particular focus on computer vision, recursive state estimation, structured prediction, optimization, and others
- Research and develop state-of-the art deep learning/machine learning models to improve our perception solutions under challenging and diverse scenarios (e.g., on highways and city streets, long-range and multi-sensor object detection, detection under degraded sensors, etc.).
- Design, prototype and evaluate machine learning algorithms and DNN architectures for detection of traffic actors, their action recognition, and semantic understanding of various traffic scenes that the Aurora Driver encounters.
- Drive performance improvements & own validation for a perception capability (e.g., Vehicle tracking, Traffic Lights, etc.)
- Integrate, test, and deploy production-ready solutions into the production code that powers the Aurora Driver.
- Excellent software engineering skills in C++ and Python
- Extensive exp in any deep learning framework, such as PyTorch, JAX, TensorFlow
- 6+ years of industry experience in Computer Vision, Machine Learning, Deep Learning, or other relevant areas of Artificial Intelligence (e.g., as evidenced by industry experience, publication record)
- Relevant industry experience (prior work on self-driving vehicles, autonomy, and/or other robotics related projects)
- Contributions to open source project(s)
- Strong track record in any field related to machine learning, as evidenced by top-tier publications
- Examples of relevant fields and conferences: computer vision (e.g., CVPR, ECCV, ICCV, IJCV), machine learning (e.g., ICML, NeurIPS, JMLR, PAMI), robotics (e.g., RSS, IJRR), graphics (e.g., SIGGRAPH, TOG