Senior Radar Perception Engineer, Obstacle Foundation Models – Autonomous Vehicles

This is a fully remote position, open to applicants in California.

📋 Description

• Enhance and refine the technical design, architecture, and roadmap for radar-based 3D obstacle perception that supports end-to-end autonomous driving.

• Perform applied research on deep learning models to optimize information extraction from radar point cloud data.

• Tackle radar perception issues such as low and inconsistent angular resolution, multipath and ghost targets, micro-Doppler signatures, and class imbalance.

• Investigate weakly-supervised pretraining and enhance radar perception by utilizing large auto-labeled datasets.

• Create and implement 3D perception models that integrate radar inputs with camera, radar, and lidar fusion.

• Develop systems for obstacle detection, tracking, and Bird’s-Eye-View scene comprehension.

• Lead the evaluation, selection, and layout optimization of radar sensors for L2-L4 autonomous driving applications.

• Construct efficient, production-ready deep learning models, from objective definition and architecture design to experimentation, training, and evaluation.

• Utilize large-scale radar pretraining, cross-modal distillation, and parameter-efficient fine-tuning techniques.

• Establish and maintain KPI frameworks for assessing radar perception performance.

• Examine real and synthetic datasets to pinpoint radar-specific failure modes and enhance accuracy, robustness, and efficiency.

• Contribute to radar data strategy, prioritize data collection and annotation, and develop model-assisted auto-labeling workflows.

• Collaborate with data and ground-truth teams.

• Work alongside safety, systems, and software teams to ensure compliance with product requirements for safety, latency, resource usage, robustness, and scalable deployment.

⛳️ Requirements

• Over 12 years of hands-on experience in developing deep learning-based perception, radar signal processing, or similar systems for complex real-world challenges.

• Strong expertise in frameworks like PyTorch.

• Proven ability to transition models from prototype stage to production.

• Demonstrated experience in data-driven development, including collaboration with data, labeling, and ground-truth teams on radar data strategy, labeling quality, and iterative model enhancement.

• Proficient programming skills in Python and/or C++.

• Experience in creating dependable, high-performance, production-quality software.

• BS/MS/PhD in Computer Science, Electrical Engineering, Robotics, or related fields, or equivalent professional experience.

• Experience in designing and deploying radar-based or multi-modal perception solutions for autonomous driving or robotics using deep learning at scale.

• Practical experience in architecting and deploying DNN-based perception pipelines on embedded or real-time platforms.

• Skills in optimizing for latency, memory, and computational constraints.

• Familiarity with contemporary architectures such as Transformers and BEV networks.

• Comprehensive understanding of radar physics and digital signal processing principles, including FMCW, beamforming, CFAR, and micro-Doppler.

• Strong publication record or recognized contributions in deep learning, radar perception, multi-sensor fusion, or autonomous systems at leading conferences or journals.

• Experience with CUDA development and optimizing training or inference pipelines through custom CUDA kernels or other GPU-accelerated components.

• Excellent communication and collaboration skills across multidisciplinary AI, hardware, and safety engineering teams.

🏝️ Benefits

• Equity

• Comprehensive benefits package