Senior Video Analytics AI Engineer - Traffic & Automation

Public Service Division; Singapore; Sur place; SGD 120 000 - 180 000; Plein temps

Résumé du poste

Public Service Division is seeking a Senior/Executive Engineer to lead the design, development and deployment of Video Analytics (VA) and Artificial Intelligence (AI) solutions for traffic management and operations in Singapore. You will shape system architecture, build AI/ML models, prepare data, and oversee deployments across on-prem and cloud environments.

The role requires hands-on work with ML pipelines, model LLMS, and cross-functional collaboration with internal and external stakeholders

Qualifications

• Knowledge of Computer Science/Engineering, Artificial Intelligence, Data Science or equivalent
• Strong communication and teamwork skills, able to work independently
• Initiative and problem-solving mindset
• Proficiency in Python, C++, C# programming languages
• Experience with MLOps, deep learning frameworks, media processing, containerization, and stream processing

Responsabilités

• Design, develop, deploy and maintain VA/AI solutions for traffic management and operations
• Develop system architecture and AI/ML models for operational use cases
• Prepare and annotate datasets, manage model deployments and integrations
• Train, optimize, test, validate and maintain AI/ML models for performance and reliability
• Collaborate with stakeholders on requirements, deployments and system integration

Connaissances

Python

C++

C#

Problem Solving

Formation

CS/Engineering or AI/Data Science

Outils

Docker

Kubernetes

FFmpeg

GStreamer

Kafka

PyTorch

TensorFlow

Description du poste

Public Service Division is seeking a Senior/Executive Engineer to lead the design, development and deployment of Video Analytics (VA) and Artificial Intelligence (AI) solutions for traffic management and operations in Singapore. You will shape system architecture, build AI/ML models, prepare data, and oversee deployments across on-prem and cloud environments.

The role requires hands-on work with ML pipelines, model LLMS, and cross-functional collaboration with internal and external stakeholders