About this role
Architect, build and maintain end-to-end AI/ML pipelines, operationalize experimental models, and implement AI/MLOps practices to deploy and monitor machine learning solutions. Optimize model inference for production, integrate models into enterprise systems using APIs and cloud services, and ensure compliance with governance and industry regulations at Seatrium's Pioneer Yard in Singapore.
Skills for this role
AI/ML pipelinesData ingestionData preprocessingModel trainingModel deploymentPredictive analyticsMonitoringAI/MLOpsCI/CD for MLModel versioningFeature storesModel inference optimizationTensorRTONNXModel pruningModel quantizationGitHubAPI integrationAWSAzureEthical AIAI governanceTroubleshootingTechnical documentationCloud-based deploymentScalability optimizationLatency optimizationProduction ML