Job Detail

Perception Engineer - Behavior Prediction at Pony
Fremont, CA, US is a startup co-located in Silicon Valley and China, our mission is to revolutionize the future of transportation by building the safest and most reliable technology for autonomous vehicles. Armed with the latest breakthroughs in artificial intelligence, we aim to deliver our technology at a global scale. We believe our work has the potential to transform lives and industries for the better.

In this role, you will:

  • Work with experts in the field of self driving vehicles on software architecture and design, system and module design, evaluation metrics, specification and implementation of test and regression frameworks.
  • Work with experts in machine learning to design and implement the state of the art deep learning and machine learning algorithms to solve open questions such as behavior prediction, decision making, and computer vision with real road test data.
  • Optimize software to run robustly under tight run-time constraints.
  • Implement user friendly tools to mine useful data from road test logs, evaluate performance, and solve real road test issues.

Minimum Qualifications:

  • Master in Computer Science, or at least 2 years of equivalent industry experience in similar technical fields.
  • Solid understanding of data structures, algorithms, parallel computing, code optimization and large scale data processing.
  • Experience in applied machine learning including data collection and analysis, evaluation and feature engineering.
  • Expertise in C++/Python.

Preferred Qualifications:

  • PhD in Deep Learning, Machine Learning, Robotics, Natural Language Processing, or similar technical field of study.
  • Experience in applying ML/DL for behavior prediction, imitation learning, motion planning.
  • Experience in deploying deep learning algorithms for real time applications, with limited computing resources.
  • Experience in convex optimization, computational geometry or linear algebra.
  • Experience in GPU/CUDA/TensorRT
  • Experience with TensorFlow