Vision & Perception AI Engineer

Design, develop, optimize, and deploy computer vision and perception AI solutions across automotive cabin intelligence, smart surveillance, industrial IoT, and factory inspection applications. Develop end-to-end perception pipelines for object detection, tracking, segmentation, activity recognition, anomaly detection, and visual reasoning using state-of-the-art CNN and transformer-based architectures.

Key Responsibilities

• Develop and optimize perception models for automotive, surveillance, industrial inspection, and edge AI applications.
• Build AI solutions for factory automation, quality inspection, defect detection, worker safety monitoring, and process compliance.
• Design and deploy multi-camera video analytics systems for smart surveillance and IoT use cases.
• Train, fine-tune, and optimize deep learning models for edge and cloud deployment.
• Collaborate with platform, embedded, and AI teams to deploy solutions on automotive SoCs, edge AI accelerators, and GPU platforms.

Required Technical Skills

• Strong understanding of Computer Vision and Deep Learning fundamentals.
• Hands-on experience with CNN-based architectures including:
  • YOLOv5, YOLOv7, YOLOv8, YOLOX
  • PP-YOLOE
  • EfficientDet
  • Faster R-CNN
  • Mask R-CNN
  • SSD
  • RetinaNet
• Experience with image classification, object detection, semantic/instance segmentation, pose estimation, and multi-object tracking.
• Experience with PyTorch, TensorFlow, ONNX, TensorRT, OpenVINO, or equivalent optimisation frameworks.
• Familiarity with edge AI deployment on NVIDIA, Qualcomm, Intel, or similar platforms.
• Knowledge of multimodal AI, Vision-Language Models (VLMs), and perception systems is a plus.

Preferred Domain Experience

• Automotive Cabin AI and Occupant Monitoring
• Smart Surveillance and Video Analytics
• Factory Inspection and Industrial Automation
• Smart Cities and Edge AI IoT Solutions
• Retail Analytics and Operational Intelligence