Senior AI Engineer – Depth Estimation and Dense Scene Understanding

About the role

Qualcomm is seeking a highly motivated Senior AI Engineer to develop next‑generation AI models for depth estimation and dense scene understanding from images and video. The role blends cutting‑edge AI research with real‑world deployment on edge devices.

Key responsibilities

• Design, develop, and optimize state‑of‑the‑art AI models for monocular, stereo, and video‑based depth estimation, as well as dense per‑pixel depth prediction and refinement.
• Research and implement techniques involving optical flow, temporal feature fusion, attention mechanisms, Video Transformers, recurrent architectures, and joint motion‑depth‑segmentation learning.
• Improve depth accuracy, geometric and temporal consistency, edge preservation, and robustness across diverse environments.
• Collaborate with hardware and system teams to create efficient AI solutions optimized for performance, power, memory, and latency on edge devices.

Required profile

• Ph.D. or M.S. in Computer Science, Engineering, Information Systems, or related field, or a Bachelor’s with 2+ years of relevant engineering experience.
• Deep expertise in computer vision and deep learning, especially in depth‑related models.
• Experience deploying AI models on edge devices and hardware‑aware model design.

Required skills

• Hands‑on experience with depth and vision models such as Depth Anything, Metric3D, UniDepth, ZoeDepth, MiDaS, RAFT, FlowFormer, DINOv2, and Segment Anything (SAM).
• Familiarity with video foundation models, self‑supervised depth learning, motion‑depth joint learning, multi‑modal vision models, neural rendering, NeRF, and Gaussian Splatting.