Senior BEV Perception Architect

Torc Robotics; Ann Arbor (MI); On-site; USD 150,000 - 230,000; Full time

Job summary

Jobtailor is seeking a senior leader in perception for autonomous systems in the United States. You will lead BEV model development, design multi-modal fusion architectures, and drive end-to-end perception solutions across camera, LiDAR, and HD maps.

You will own large-scale training pipelines, improve robustness, and mentor ML engineers while pushing forward self-supervised learning and foundation models for 3D perception.

Qualifications

• 10+ years of experience in deep learning for perception, 3D vision, and/or autonomous systems.
• Proven expertise in BEV modeling, 3D scene understanding, and multi-view fusion.
• Strong background in multi-modal sensor fusion, particularly camera and LiDAR data.
• Experience with large-scale data pipelines and distributed training.
• Publications or open-source contributions in top-tier venues.

Responsibilities

• Lead BEV model development and execute the technical roadmap for BEV-based perception models across detection, segmentation, road topology, and scene understanding
• Design multi-modal architectures that fuse camera, LiDAR, radar, and HD maps into unified spatial representations
• Develop foundational perception models using BEV transformers, voxel-based encoders, or implicit scene representations
• Own large-scale training workflows, including data sampling, augmentation, distributed training, and hyperparameter optimization
• Improve model robustness and generalization for low visibility, occlusions, and rare scene configurations
• Establish evaluation frameworks for geometric accuracy, temporal stability, and cross-domain transfer performance
• Collaborate with sensor calibration, mapping, and fusion teams on cohesive perception model interfaces
• Mentor and guide ML engineers while cultivating experimentation, code quality, and model validation best practices
• Explore self-supervised learning, large-scale pretraining, and foundation models for 3D perception

Skills

BEV Modeling

3D Scene Understanding

Multi-Modal Sensor Fusion

Deep Learning Frameworks (PyTorch, TF)

Python

Distributed Training

Experiment Management

Mentoring

Education

M.S. or Ph.D. in Computer Science

Electrical Engineering

Robotics

Tools

Ray

TensorFlow

PyTorch

Experiment Management Systems

Job description

Jobtailor is seeking a senior leader in perception for autonomous systems in the United States. You will lead BEV model development, design multi-modal fusion architectures, and drive end-to-end perception solutions across camera, LiDAR, and HD maps.

You will own large-scale training pipelines, improve robustness, and mentor ML engineers while pushing forward self-supervised learning and foundation models for 3D perception.