Principal Perception Engineer – Obstacle Foundation Models, Autonomous Vehicles

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

📋 Description

• Take ownership of the technical vision, architecture, and roadmap for 3D obstacle perception that supports end-to-end autonomous driving.

• Create and develop 3D perception models utilizing multi-camera inputs and/or the fusion of camera, radar, and lidar sensors.

• Lead the development of efficient, production-ready deep learning models.

• Establish objectives, select architectures, guide experimentation, and set best practices for training and evaluation.

• Define and implement KPI frameworks to measure perception performance.

• Analyze extensive real and synthetic datasets to identify failure modes and enhance accuracy, robustness, and efficiency.

• Direct the perception data strategy, encompassing data and labeling requirements, collection, annotation, active learning, auto-labeling, VLMs, and model-in-the-loop tooling.

• Collaborate with safety, systems, and software teams to fulfill product requirements regarding safety, latency, resource utilization, and software robustness.

• Ensure deployment readiness at scale.

• Provide technical leadership and mentorship across perception and autonomy teams.

⛳️ Requirements

• Over 15 years of hands-on experience in developing deep learning-based perception or closely related systems to address complex real-world challenges.

• Strong expertise in frameworks such as PyTorch.

• Proven success in transitioning models from prototype to production.

• Demonstrated technical leadership as a senior or principal-level contributor.

• Experience in owning features or subsystems end-to-end, setting technical direction, making architectural decisions, and coordinating across teams.

• Established experience in data-driven development, including collaboration with data, labeling, and ground-truth teams.

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

• A history of creating reliable, high-performance, production-quality software.

• Excellent communication and collaboration abilities.

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

• Experience leading perception solutions for autonomous driving or robotics using camera-based deep learning at scale.

• Familiarity with architecting and deploying DNN-based perception pipelines on embedded or real-time platforms.

• Experience in optimizing latency, memory, and computational constraints.

• Knowledge of CNNs, transformers, large-scale pretraining, parameter-efficient fine-tuning methods such as LoRA, and vision-language models.

• A strong publication record or recognized contributions in deep learning, computer vision, or autonomous systems.

• In-depth understanding of 3D computer vision, including camera modeling and calibration, multi-view geometry, and 3D representations.

• Experience with CUDA development and GPU-accelerated components.

🏝️ Benefits

• Equity

• Benefits