{"@context":"https://schema.org/","@type":"JobPosting","title":"Computer Vision Engineer
microTECH Global Limited
5 days ago
Role details
Contract type
Permanent contract Employment type
Full-time (> 32 hours) Working hours
Regular working hours Languages
English Experience level
SeniorJob location
Tech stack
Computer Vision
C++
Nvidia CUDA
Image Quality
Python
Object Detection
OpenCV
TensorFlow
Software Deployment
Software Engineering
Visual Systems
PyTorch
Information Technology
Low Latency
ONNX (Open Neural Network Exchange) Format
TensorRT
Lidar
Job description
- Own camera-based perception pipelines from sensor selection to production deployment
- Evaluate and select camera sensors, modules, and optics based on system and application requirements
- Tune and optimize ISP pipelines (image quality, color, HDR, noise, latency, synchronization)
- Develop and integrate computer vision and ML-based algorithms into the perception stack
- Work with perception and software teams to integrate cameras with other sensors (LiDAR, IMU, radar, etc.)
- Design and deploy real-time vision systems on embedded and edge compute platforms
- Implement and optimize models for tasks such as object detection, tracking, and segmentation; depth estimation from cameras (mono, stereo, multi-view); optical flow and motion estimation
Requirements
- Bachelor's degree or higher in Computer Science, Electrical Engineering, Robotics, or a related field
- 7+ years of experience in camera, computer vision, or perception engineering
- Strong experience with camera sensors, optics, and ISP tuning
- Deep understanding of computer vision and ML fundamentals
- Hands-on experience developing and deploying ML-based vision models
- Strong software engineering skills in C++ and/or Python
Desirables:
- Experience in robotics, autonomous systems, AR/VR, or advanced driver assistance systems (ADAS)
- Familiarity with modern vision and ML frameworks (PyTorch, TensorFlow, ONNX, OpenCV, etc.)
- Experience with embedded or edge AI deployment (NVIDIA Jetson, CUDA, TensorRT, etc.)
- Background in depth estimation, stereo vision, SLAM, or visual-inertial systems