Stack is developing revolutionary AI and advanced autonomous systems designed to enhance safety, reliability, and efficiency of modern operations. The Auto Labeling team at Stack develops large ML models that leverage state-of-the-art multi-sensor fusion techniques, integrating data from lidars, cameras, radars, and IMUs. The goal is to generate high-quality labeled data, essential for training and evaluating Stack's onboard perception models.
Requirements
- 3+ years building ML systems
- Experience with distributed training systems
- Strong Python engineering skills, particularly PyTorch
- Strong experience with GPUs; CUDA experience is a plus
Responsibilities
- Design, evaluate, and deploy acausal large ML models for high-quality labeled data generation from multi-sensor inputs.
- Work with state-of-the-art techniques in large-scale distributed model training and evaluation.
- Collaborate with onboard and offboard downstream consumers throughout the development lifecycle, from requirements gathering to evaluation and ongoing communication.
- Contribute to the overarching vision of building safety-critical and robust onboard and offboard perception systems.
- Uphold Stack’s culture of engineering excellence.
Other
- Degree in Computer Science, Machine Learning, Robotics, or related field
- Master's or PhD preferred
- Autonomous vehicle space experience is a plus
- Ability to work in a fast-paced startup environment while maintaining high-quality standards
- This position may be contingent upon Stack AV verifying a candidate’s residence, U.S. person status, and/or citizenship status.
