Image Signal Processing Algorithm Engineer

PERSOL SINGAPORE PTE. LTD.; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

PERSOL SINGAPORE PTE. LTD. is seeking a PhD-level researcher to advance image and video processing for autonomous driving, machine vision, and professional photography products. You will explore perception algorithms and contribute to end-to-end solutions on embedded platforms.

Collaborate with cross-functional teams in sensor fusion, planning, and control; publish findings, file patents, and stay abreast of the latest video processing standards and industry trends.

Qualifications

• PhD in Computer Science, Robotics, Electrical Engineering, or related field with a focus on computer vision, machine learning, or robotics perception.
• Basic knowledge in digital signal processing and AI-based low-level computer vision approaches.
• Familiar with deep learning frameworks (TensorFlow, PyTorch) and C/C++.

Responsibilities

• Participate in research of advanced image/video processing algorithms for autonomous driving, machine vision, and photography products.
• Design and implement advanced perception algorithms in 3D vision, VLMs/VLA, or world models.
• Collaborate with cross-functional teams to deliver end-to-end solutions and deploy on embedded platforms.
• Publish research findings, file patents, and stay updated with video processing standards.

Education

PhD in Computer Science, Robotics, Electrical Engineering, or related field with focus on computer vision, machine learning, or robotics perception

Tools

C/C++

OpenCV

TensorFlow

PyTorch

ASIC design familiarity

Job description

Key Responsibilities:

• Participate in research of advanced image/video processing algorithms using for autonomous driving, machine vision, and professional photography products.
• Research, design, and implement advanced perception algorithms in one or more of the following areas:
• 3D vision (stereo vision, structure-from-motion, SLAM, LiDAR-camera fusion, depth estimation)
• Vision-Language Models (VLMs) / Vision-Language Alignment (VLA)
• World models for robotics and autonomous driving perception & prediction
• Collaborate with cross-functional teams in sensor fusion, planning, and control to deliver end-to-end solutions.
• Publish research findings, file patents, and keep track of cutting-edge academic and industrial progress in the field.
• Contribute to scalable deployment of algorithms on embedded platforms.

Required Qualifications/Skills:

• PhD in Computer Science, Robotics, Electrical Engineering, or related field with a focus on computer vision, machine learning, or robotics perception.
• Basic knowledge in digital signal processing and AI based low-level computer vision approaches
• For deep learning projects, familiar with at least one deep learning framework such as tensorflow, pytorch, etc.
• Working knowledge of C/C++ and/or OpenCV.
• Familiarity with ASIC design approach and environment will be an advantage
• Research in image/video signal processing algorithms like noise removal, image enhancement, signal processing for digital cameras.
• Perform research into leading edge and emerging video technologies, ideas, approaches and keep up to date with new video processing standards and general industry trends
• Pruning, model optimization, and deployment of AI-based video/image processing algorithms on chipset.
• Machine vision-oriented video/image enhancement algorithm research and development
• C-model simulation for image/video signal processing algorithm development and verification.
• Ability to express ideas and communicate effectively.
• Any of the following skills and experiences would be an added advantage:
• Video algorithms for pre-processing, post-processing, video sharpening, temporal/spatial noise reduction, color consistency, etc.
• Key image processing algorithms for Camera Signal Processing cores

We regret to inform that only shortlisted candidates will be notified.