Develop cutting-edge spatio-temporal deep learning models to enhance perception capabilities in autonomous driving systems. Focus on real-time detection, segmentation, and sensor fusion using data from cameras, radar, and LiDAR to build robust, scalable solutions for dynamic environments.
What You'll Do
- Design and implement machine learning models that process multi-sensor data across time and space for accurate environmental understanding.
- Analyze raw sensor inputs and stay current with advancements in deep learning and computer vision to inform model architecture decisions.
- Lead the transition of experimental models from lab environments to real-world test tracks and public roads, ensuring reliability and performance at scale.
- Collaborate closely with roboticists and perception engineers to refine algorithms, conduct prototyping, and support end-to-end deployment.
- Write clean, efficient code in Python and C++ for perception modules that integrate seamlessly with broader system components.
- Champion best practices in software engineering and help maintain high technical standards across the team.
Requirements
- Bachelor’s or Master’s degree in Computer Science, Electrical Engineering, Robotics, or a related technical field.
- Minimum of 7 years of professional experience in software development with a focus on machine learning applications.
- Demonstrated expertise in deep learning frameworks such as PyTorch or TensorFlow.
- Proven experience building and deploying computer vision or perception systems using camera, radar, or LiDAR data.
- Strong background in computer vision, point cloud processing, and real-time perception pipelines.
- At least 5 years of hands-on development in Python and C++ in production environments.
- Track record of delivering computer vision products to market at scale.
Preferred Qualifications
- Ph.D. in a relevant field with a focus on machine learning, or equivalent practical experience.
- Experience developing temporal models that leverage sequences of data, such as video-based activity recognition or frame aggregation for improved accuracy.
Technical Stack
PyTorch, TensorFlow, Computer Vision, Deep Learning, Multi-sensor Fusion, 3D Object Detection, Lane Line Detection, State Estimation, Scene Segmentation, Point Cloud Processing, C++, Python
Benefits
- Competitive base salary with additional compensation through annual bonuses and equity participation
- Comprehensive medical, dental, and vision coverage for individuals and families
- Employer-matched 401(k) with immediate vesting and health savings account with employer contributions
- Group term life insurance provided by employer; optional supplemental coverage available
- Paid parental and medical leave
- Unlimited vacation policy and 13 paid holidays annually
- Daily meals, snacks, and beverages available at all office locations
- Pre-tax commuter and dependent care spending accounts
- Monthly wellness stipend and professional development reimbursement
- Support programs for adoption, surrogacy, backup child and elder care
- Employee assistance program and access to discounted legal, pet insurance, and identity protection services
- Team engagement initiatives including employee resource groups and quarterly activity funding
