Sr. Computer Vision Engineer (3D Semantic Scene Understanding)

5 months ago

Munich, GermanySenior

Responsibilities

Develop 3D semantic scene reconstruction algorithms using geometric primitives, semantic labels, surface reconstruction, occupancy mapping, and volumetric segmentation.
Architect multimodal fusion systems combining panoptic segmentation representations with 3D models.
Augment spatio-temporal knowledge graphs with reconstructed 3D spatial data and structural relationships.
Design agentic workflows for reasoning and inference over complex 3D environments and knowledge graphs.
Implement actionable affordance mapping based on physical geometry and engineering logic.
Deploy models, representations, and inferred domain context into scalable production use cases.

MS or PhD in Computer Science, Robotics, Electrical Engineering, or a related field.
At least 3 years of industry experience in computer vision and deep learning.
At least 2 years of experience leading 3D computer vision projects, especially geometric deep learning and 3D reconstruction.
Exceptional implementation experience with Open3D, PyTorch 3D, and reconstruction methods including multi-view stereo, surface reconstruction, mesh fitting, TSDF, and 2D-to-3D lifting.
Thorough understanding of software design and fluent, articulate English communication.
Experience with physics engines such as NVIDIA Isaac Gym, MuJoCo, or PyBullet is preferred.
Experience implementing agentic AI with GraphRAG, LangGraph, or LlamaIndex is preferred.
Previous experience in a fast-paced technology startup environment is preferred.

Competitive compensation with significant equity upside.
High autonomy in shaping multimodal scene understanding and reasoning capabilities.
Opportunity to work with a global team of ML engineers, software engineers, and industry practitioners.
Work at the forefront of AI for construction technology.

11-50 employees