Computer Vision Engineer - Robotic Perception & 3D...

Design, develop, and deploy robotic perception algorithms for real-world systems, with emphasis on learned 3D understanding.

Develop and evaluate models for: 3D reconstruction and depth estimation

Feature detection, matching, and multi-view geometry

Semantic and instance segmentation

6-DoF object pose and shape estimation

Integrate perception algorithms with robotic platforms and sensor stacks, including RGB/RGB-D cameras, LiDAR, IMU, and other vision-based sensors.

Own perception components across the full lifecycle: data collection, calibration, model development, validation, optimization, and system integration.

Collaborate with robotics, controls, and systems teams to ensure perception outputs meet real-time, accuracy, and robustness requirements.

Actively contribute to system architecture, algorithm selection, and performance trade-offs across accuracy, latency, and compute constraints.

Engage with internal and external research partners to explore and transition new computer vision and robotic perception technologies into applied systems.

We are seeking a Computer Vision Engineer with deep expertise in robotic perception and learned 3D scene understanding. This role focuses on developing and integrating advanced perception algorithms that enable robots and autonomous systems to understand, localize, and interact with the physical world.

The ideal candidate has hands-on experience with 3D reconstruction, depth prediction, feature matching, semantic segmentation, and 6-DoF object pose and shape estimation, and can take perception algorithms from research concepts through system-level integration and deployment., BS + 5 years, MS + 3 years, or PhD in Computer Science, Electrical Engineering, Mechanical Engineering, Robotics, or a related field with a focus on computer vision or perception.

Strong experience developing computer vision and robotic perception software for real-world systems.

Demonstrated expertise in one or more of the following areas: Learned depth prediction and 3D reconstruction

Multi-view geometry and feature matching

Semantic / instance segmentation

6-DoF object pose estimation and shape inference

Proficiency in C/C++ and Python for perception and robotics applications.

Experience with software architecture, system design, and integration in complex, multi-sensor systems.

Hands-on experience integrating perception software into working robotic or autonomous systems.

Strong problem-solving skills and ability to operate independently in a fast-paced, research-driven environment. Experience translating high-level autonomy or robotics requirements into concrete perception solutions.

Familiarity with modern deep learning frameworks used in computer vision (e.g., PyTorch, TensorFlow).

Strong communication skills, with the ability to explain complex technical concepts to cross-functional stakeholders.

Self-driven, innovative, and comfortable exploring new technical areas within robotic perception and computer vision.