Job Description:
Responsible for designing, developing, and maintaining comprehensive Product platforms that integrate real-time data pipelines, predictive analytics, and interactive 3D visualizations. The Products include Virtual Testing Environment, Design Opimisation Toolkit and Digital Twin. This role encompasses system architecture, data engineering, cloud infrastructure, and frontend development to deliver a scalable, secure, and high-performance solution for live monitoring, simulation, and operator interaction, in collaboration with domain experts in hydrodynamics, structures, structural health monitoring, controls, and AI.
Key Responsibilities
- Design and implement the end-to-end architecture for cloud, hybrid, and on-prem Product deployments, ensuring scalability, performance, and security
- Develop and integrate backend services, data pipelines, and APIs for real-time and batch data ingestion, processing, storage workflows, simulation automation, and machine learning/AI model serving
- Integrate physics-based simulations, machine learning/AI inference services, and analytics into unified Product workflows
- Design and operate a Virtual Testing Environment and Design Optimisation Toolkit for batch simulation execution, scenario orchestration, regression testing, optimisation, sensitivity & uncertainty analyses and Digital Twin verification and validation
- Integrate data, simulation results, and machine learning/AI outputs into dashboards and interactive 3D visualizations
- Enable real-time monitoring, alerting, and scenario-based analysis
- Standardize data and model structures, and manage versioning and lifecycle of models and services
- Implement and maintain CI/CD pipelines and DevOps/MLOps practices for reproducible deployment and operations
Requirements / Skills
- Strong experience in system and cloud architecture for data-intensive platforms
- Proficiency in backend development, data engineering, and API integration
- Experience with real-time data streaming, time-series processing, and analytics
- Hands-on experience deploying and operating machine learning/AI models (inference, versioning, monitoring)
- Experience integrating dashboards and real-time 3D visualization technologies
- Knowledge of containerization, orchestration, and DevOps/MLOps practices
The above eligibility criteria are not exhaustive. A.STAR may include additional selection criteria based on its prevailing recruitment policies. These policies may be amended from time to time without notice. We regret that only shortlisted candidates will be notified.
