Senior AI Engineer – Depth Estimation and Dense Scene Understanding
Core
Develop next-generation AI models for depth estimation and dense scene understanding from images and video, focusing on monocular, stereo, metric, and video-based depth estimation for edge devices.
Role type
Senior IC machine-learning engineer (computer vision)
Builds
Production AI models for spatial understanding on edge devices
Domain
Computer Vision / Deep Learning / Edge AI
Deliverable
production ML models
Required skills
Monocular depth estimation, Stereo depth estimation, Video-based depth estimation, Dense per-pixel vision models, Optical flow estimation, Temporal modeling, Semantic segmentation, Geometric vision, 3D perception, Neural network architecture design, Hardware-aware model design, System-level optimization
Preferred skills
Depth Anything, Metric3D, UniDepth, ZoeDepth, MiDaS, RAFT, FlowFormer, DINOv2, Segment Anything (SAM), Video foundation models, Self-supervised depth learning, Neural rendering, NeRF, Gaussian Splatting, Edge AI deployment
Technologies
Transformers, Recurrent architectures, Memory-based architectures, Video Transformers
Responsibilities
Design and optimize AI models for various depth estimation tasks; Develop novel architectures to improve depth accuracy and temporal consistency; Research and implement techniques leveraging temporal information and motion cues for video understanding.
Seniority
Senior, hands-on IC
