Lucid Motors
Perception Software Engineer, Autonomous Driving
About this role
Lucid seeks a Perception Software Engineer to develop and integrate ML-based perception systems for autonomous driving, focusing on bird's-eye-view transformer models and production-ready solutions. You'll collaborate across ML, embedded, and systems teams to deploy optimized models on vehicle platforms while maintaining MISRA/AUTOSAR compliance.
What you'll do
- Research and integrate BEV transformer models for perception tasks in the ADAS stack
- Develop state-of-the-art ML-based prediction solutions for production perception systems
- Write and optimize production-grade C++ code following MISRA/AUTOSAR standards
- Deploy and optimize ML models on embedded platforms like NVIDIA Drive Orin/Xavier
- Develop comprehensive unit and integration tests with diagnostic pipelines
- Debug performance bottlenecks and resolve static analysis violations
What they're looking for
- Deep learning algorithms (object detection, tracking, segmentation)
- Bird's-eye-view (BEV) transformer models
- C++ and embedded systems development
- ML deployment pipelines and GPU inference optimization
- Embedded operating systems (QNX, Ubuntu, NVIDIA Drive)
- MISRA/AUTOSAR standards compliance
- Git and collaborative development workflows
- Bash scripting for automation
Benefits
- Medical, dental, and vision insurance
- Life and disability coverage
- 401(k) retirement plan
- Paid time off (160 hours annually for salaried employees)
- Equity program participation
- Discretionary annual cash incentive program
Opens the official application on the employer’s site. No login required.
Lucid Motors
Lucid Motors manufactures electric vehicles and is hiring quality engineers to improve production processes and resolve customer issues at their Arizona facility. The company is looking for manufacturing and field quality professionals to drive process improvements, investigate warranty concerns, and enhance overall vehicle performance.
- Website
- lucidmotors.com
Likely interview questions
- Describe your experience developing or deploying BEV transformer models—what were the key challenges and how did you address them?
- Walk us through how you've optimized ML model inference on embedded platforms, and what trade-offs you made between accuracy and performance.