Computer Vision Engineer – Autonomy & Perception

Pivotal•Palo Alto, CA

10d•Onsite

About The Position

The Autonomy team at Pivotal develops advanced autonomy capabilities for our aircraft, enabling safe, precise, and reliable mission execution from takeoff to landing. We are seeking a Computer Vision Engineer to support the development of next-generation perception systems for our autonomous aerial platforms, including the Helix family of systems. In this role, you will collaborate with autonomy, guidance, navigation and control (GNC), flight software, and AI engineers to design, implement, and deploy computer vision algorithms that operate effectively in dynamic, real-world environments. You will work across object detection, tracking, visual localization, scene understanding, sensor fusion, and perception-driven autonomy to enable robust autonomous operations in challenging mission scenarios. The ideal candidate combines strong computer vision fundamentals with practical experience deploying perception systems on robotic or autonomous platforms. You will play a key role in developing vision capabilities that support navigation, obstacle avoidance, target tracking, and mission autonomy while contributing to the broader autonomy stack deployed on operational aircraft.

Requirements

Bachelor's degree in Computer Science, Robotics, Electrical Engineering, Aerospace Engineering, or a related technical field.
2–4 years of industry experience in computer vision, robotics, machine learning, or autonomous systems OR Master's degree with 1–2 years of industry experience.
Strong proficiency in C++, Python, or Rust.
Experience with OpenCV and modern computer vision frameworks.
Experience developing perception systems using PyTorch, TensorFlow, or similar machine learning frameworks.
Strong understanding of image processing, geometric vision, and camera systems.
Experience with object detection, tracking, segmentation, and machine learning-based perception algorithms.
Familiarity with sensor fusion and state estimation techniques.
Experience with ROS/ROS2 or similar robotics middleware.
Experience developing software in Linux environments.

Nice To Haves

Master's or PhD in Computer Vision, Robotics, Machine Learning, Computer Science, or a related field.
Experience with autonomous aircraft, UAVs, robotics, or aerospace systems.
Experience with visual SLAM, visual-inertial odometry, or localization systems.
Knowledge of camera calibration, multi-camera systems, and geometric computer vision.
Experience integrating lidar, radar, thermal cameras, and inertial sensors into perception systems.
Experience deploying AI models on embedded platforms such as NVIDIA Jetson or similar edge computing hardware.
Familiarity with simulation environments such as Gazebo, Isaac Sim, AirSim, or equivalent.
Experience optimizing perception systems for real-time performance and resource-constrained platforms.
Contributions to open-source robotics, autonomy, or computer vision projects.
Familiarity with defense industry standards and security clearance processes.

Responsibilities

Design and develop perception systems for autonomous aerial platforms operating in GPS-denied and contested environments; implement object detection, classification, segmentation, and tracking algorithms using RGB, thermal, and multimodal sensor data; develop visual perception pipelines for obstacle detection, collision avoidance, and situational awareness; build scene understanding capabilities to support autonomous navigation and mission execution; evaluate and integrate state-of-the-art computer vision and AI techniques into operational systems.
Develop visual-inertial odometry, localization, and mapping algorithms; implement vision-based navigation solutions for degraded and GPS-denied environments; support SLAM and feature-based localization systems; design robust estimation methods that fuse camera, IMU, GPS, lidar, and radar data; improve navigation performance through sensor fusion and environmental awareness.
Develop, train, and deploy deep learning models for onboard perception; create data processing, labeling, augmentation, and evaluation pipelines; optimize neural networks for real-time inference on embedded computing platforms; analyze model performance and improve robustness across operational conditions; support deployment of perception models on edge AI hardware.
Integrate and evaluate diverse imaging systems including RGB, stereo, fisheye, thermal, and event-based cameras; develop camera calibration workflows and sensor characterization procedures; support multi-camera synchronization and calibration efforts; improve image quality, calibration accuracy, and perception system reliability; collaborate with hardware teams to evaluate and integrate emerging sensor technologies.
Develop simulation and testing frameworks for perception algorithms; support software-in-the-loop, hardware-in-the-loop, and flight testing activities; analyze flight data to identify performance gaps and improve perception robustness; establish metrics and validation procedures for autonomous perception systems; document system performance and support field deployments.