MLOps Engineer

About the Opportunity Our client, a globally recognized media and information organization, is building out the operational foundation for large-scale production machine learning systems supporting enterprise intelligence products. This role focuses on deploying, operating, scaling, and governing ML infrastructure and inference services across multimodal AI workloads involving text, image, and video processing. The environment is highly technical and collaborative, with a strong emphasis on production reliability, scalability, observability, and AWS-based ML infrastructure. What You’ll Be Doing Design, deploy, and operate production ML infrastructure across Dev, QA, and Prod environments Manage ML deployment pipelines and runtime operations in AWS SageMaker Configure and optimize GPU/CPU infrastructure for large-scale inference workloads Implement monitoring, alerting, drift detection, and observability for ML systems Build deployment governance processes including rollout, rollback, and recovery strategies Support high-throughput ML workloads across text, image, and video pipelines Optimize infrastructure scalability, cost efficiency, and operational reliability Partner with ML Engineers and Data Scientists to operationalize new models and workflows Implement A/B testing and controlled rollout strategies for production ML systems Required Qualifications Hands-on experience deploying and operating ML systems in production Strong AWS SageMaker experience, including: Pipelines Endpoints Monitoring Multi-environment deployments Experience with containerized ML deployment and orchestration Experience operating PyTorch and TensorFlow inference systems Strong understanding of autoscaling, infrastructure optimization, and runtime reliability Experience implementing monitoring and observability frameworks for ML systems Experience supporting distributed ML workloads in cloud environments Strongly Preferred Experience supporting NLP and computer vision ML systems Familiarity with semantic/vector search infrastructure Experience with ranking/reranking systems Familiarity with ANN/vector indexing approaches Experience supporting large-scale text, image, and video processing pipelines Experience optimizing GPU-based infrastructure What This Role Is Production MLOps Engineering ML Infrastructure & Deployment Runtime Reliability & Scalability AWS ML Operations Monitoring & Operational Governance What This Role Is Not Pure DevOps Model Architecture Design Data Science Ownership Research ML Engineering Additional Details Fully remote Preference for East Coast collaboration hours Applicants must be legally authorized to work in the United States and must not require employer sponsorship now or in the future. Show more Show less