Point One Navigation

Point One Navigation

Staff Computer Vision Engineer

San Francisco HQ · Staff+

Sponsorship not specifiedDetected 11 days ago
PythonC++AlgorithmsDeep LearningTensorFlowPyTorchComputer VisionRoboticsSensorsResearchLeadershipCollaboration

About the role

  • FusionEngine already powers a wide range of devices, hardware platforms, and customer applications.
  • Raise the Technical Bar - Mentor junior engineers and establish best practices across the team. - Contribute to architecture discussions, technical strategy, and roadmap planning.

Responsibilities

  • Spatial data, coordinate frames, and map layers are exposed via clean data models and APIs, empowering our UI and infrastructure teams to build seamless user-facing applications.
  • Design and own a rigorous benchmarking framework to continuously evaluate the accuracy, latency, compute footprint, and reliability of internal code versus off-the-shelf and vendor technologies.
  • Collaborate tightly with infrastructure and UI engineers to manage data products, render maps, and track assets for the end user.
  • Understand how and work with the larger navigation team to use camera data with GNSS, IMU, wheel odometry, and other indoor positioning signals to maintain high-confidence state estimation for moving agents in all environments.
  • Drive performance tuning for edge deployment to ensure tracking algorithms run with low latency and high reliability on constrained compute architectures.
  • Our RTK corrections network and FusionEngine™ software deliver centimeter-level accuracy and high-confidence positioning for vehicles, robots, drones, and devices across industries in outdoor applications.
  • Proactively identify failure modes in tracking and mapping and design robust algorithmic fallbacks.
  • you will conceptualize and drive complex technical challenges end-to-end - from early architecture through deployment in mission-critical systems - while raising the technical bar across the team.

Requirements

  • Expertise in modern C++ (C++14 or later) and Python, with a demonstrated history of success of taking AI model prototypes (PyTorch, TensorFlow) and turning them into scalable, real-time production systems.
  • Expertise in ROS1/ROS2.
  • Hands-on experience with Visual SLAM, 3D reconstruction, and mapping architectures.
  • Experience in deploying semantic segmentation/object detection in real-world environments.
  • Ability to take high-level research and business goals and decompose them into actionable engineering tasks, realistic schedules, and clear milestones.
  • Experience in deploying multi-object tracking and ReID architectures in real-world, dynamic environments.
  • Familiarity with managing large-scale point clouds, mesh generation, or NeRFs/Gaussian Splatting for environmental representation.
  • This environment gives people a high level of autonomy and the ability to make a real impact.
  • 7+ years of professional algorithm and software development experience, with significant depth in applied research, computer vision, or robotics.
  • Experience with multi-view geometry, camera calibration, and fusing vision with other sensor modalities (IMU, GNSS).
  • MS or PhD in Computer Science, Robotics, or equivalent experience.
  • Bonus Points For
  • Background in deploying optimized vision models to edge devices using TensorRT, ONNX, or platform-specific accelerators.
  • At Point One, our cultural and operating design is built around one guiding principle: we must move with extreme speed and efficiency of effort to stay in a leadership position.

Benefits

  • Vision pipelines automatically generate and maintain accurate, semantically rich maps of complex indoor environments with minimal manual intervention.
  • Develop or integrate deep learning and classical CV algorithms to extract semantic information from environments (e.g., structural elements, zones, and specific objects) for overlay onto base map.

Company info

  • Trust / Assume Best Intent - Trust allows us to move fast. When we start from trust, we spend no time second-guessing or looking for ulterior motives and thus focus all our energy on acting.
  • High Output, Action Oriented - Our default posture is "yes." We bias toward action and deliver results quickly, knowing that speed and efficiency compound into impact as we unblock others around us.
  • Divine Discontent - We're never satisfied with the status quo and are self-motivated to improve ourselves, our work, and our company. We actively seek feedback in real-time to shorten improvement cycles.
  • No Ego, One Team - Collaboration without ego creates leverage. When we win as one team, we eliminate friction and move faster together.
  • Self Accountability - Taking ownership is the straightest line to learning, self-improvement, and correcting our course of action. And blaming others around us is a fast path to destroying trust.
  • Edge Innovation - We bias toward action over approval. Experiment, decide, and move - failure is just a step toward faster learning.
  • No Hierarchies - We practice self-prioritization and go direct to the source. Flattening layers reduces drag and maximizes autonomy.
  • Customer Experience First - We optimize for the end-to-end customer outcome, not functional or departmental efficiency. This focus cuts waste, aligns priorities, and ensures we spend effort where it matters most.
  • We are actively broadening our expertise into indoor environments to provide the same high-standard localization and navigational quality for users everywhere.
Apply directly at Point One Navigation →Create a free account for alerts like thisView Point One Navigation immigration profile

This listing is sourced directly from Point One Navigation's careers page and normalized into a canonical job model.