Principal Investigator – 3D AI, Computer Vision & Spatial Computing

Principal Investigator – 3D AI, Computer Vision & Spatial Computing

Location: Remote
Employment Type: Full-Time
Education: PhD Required
Topic Title: Dynamically Generated, Articulated 3-Dimensional Training Content

Position Overview

Arch Systems is seeking a Principal Investigator (PI) to lead applied research focused on AI-assisted generation of interactive, articulated 3D content from sparse visual and technical data.

The ideal candidate will have a strong research background in 3D Computer Vision, Computer Graphics, Robotics, Neural Rendering, 3D Reconstruction, Articulated Object Understanding, Multimodal AI, or Spatial Computing.

The PI will provide scientific and technical leadership for transforming photographs, video, CAD/technical diagrams, and procedural documentation into semantically structured, manipulation-ready 3D assets for deterministic procedural training in immersive environments.

Key Responsibilities

• Lead applied research in 3D reconstruction, neural rendering, NeRF, Gaussian Splatting, semantic part recovery, articulated-object modeling, and interaction geometry.
• Develop methods for inferring component hierarchies, joints, axes, motion constraints, attachments, collision geometry, and affordances from visual and technical data.
• Apply multimodal AI/VLM techniques to connect reconstructed 3D components with engineering documentation and authoritative technical information.
• Research approaches for converting maintenance procedures into deterministic actions, states, prerequisites, and interactive training behaviors.
• Design controlled experiments, ground-truth datasets, evaluation methodologies, and quantitative feasibility studies.
• Lead technical publications, invention disclosures, patents, demonstrations, and government R&D deliverables.
• Provide technical guidance to engineers developing Python/PyTorch computer vision pipelines and Unity/OpenXR immersive applications.
• Serve as the technical authority during customer reviews, technical demonstrations, and transition planning.
• Collaborate with multidisciplinary teams across AI, computer vision, graphics, robotics, software engineering, and immersive technologies.

Required Qualifications

• PhD in Computer Science, Computer Engineering, Robotics, Electrical Engineering, Computer Vision, Computer Graphics, or a closely related technical field.
• Demonstrated research experience in 3D Computer Vision, 3D Computer Graphics, Robotics, or related areas.
• Strong programming experience with Python and PyTorch.
• Experience with one or more of the following:
• 3D Reconstruction
• Neural Rendering
• NeRF
• Gaussian Splatting / 3D Gaussian Splatting
• Semantic Segmentation
• Articulated Object Modeling
• Computer Vision
• Multimodal AI / Vision-Language Models
• 3D Scene Understanding
• Robotics or Manipulation
• Demonstrated research accomplishments through peer-reviewed publications, patents, invention disclosures, sponsored research, or government R&D projects.

Preferred Technical Experience

Experience with one or more of the following technologies is highly desirable:

• COLMAP
• Open3D
• PyTorch3D
• Nerfstudio
• Gaussian Splatting
• OpenCV
• Segmentation / VLM models
• Unity
• OpenXR
• AR/VR or Extended Reality (XR)
• Robotics simulation
• 3D asset generation and procedural modeling
• CAD or engineering documentation
• Kinematics, motion planning, or robotic manipulation

Ideal Candidate

The ideal candidate is a hands-on research leader who can bridge advanced AI/3D vision research with practical engineering applications. Experience taking research concepts from prototype and experimentation through demonstration, technical publication, and customer transition is highly valued.

Candidates with backgrounds as Principal Investigator, Principal Scientist, Research Scientist, Applied Scientist, Research Engineer, Computer Vision Scientist, Computer Vision Engineer, Robotics Researcher, or Computer Graphics Researcher are encouraged to apply.

Keywords

3D Computer Vision, Computer Vision, 3D Reconstruction, 3D Vision, Computer Graphics, Neural Rendering, NeRF, Gaussian Splatting, 3D Gaussian Splatting, Articulated Objects, Object Understanding, Semantic Segmentation, Part Segmentation, Kinematics, Robotics, Robotic Manipulation, Affordances, Multimodal AI, Vision-Language Models, VLM, Python, PyTorch, COLMAP, Open3D, PyTorch3D, Nerfstudio, OpenCV, Unity, OpenXR, AR, VR, XR, Spatial Computing, 3D Scene Understanding, CAD, Simulation, AI Research, Applied Research, R&D, Principal Investigator, Principal Scientist, Research Scientist, Research Engineer.