MLOps Engineer

Visionet Systems Inc.New York, United States
ContractOn-siteJuniorLimited info disclosed
22 views0 applications

Description

Partnering with ML Engineers, Data Scientists, and Platform Engineering, the MLOps Engineer owns the production lifecycle of machine‑learning systems. This role is responsible for deploying, operating, scaling, monitoring, and governing ML workloads so they run reliably, securely, and cost‑effectively in production. The MLOps Engineer ensures that models and inference pipelines built by ML Engineers can be safely promoted across Dev, QA, and Prod, meet operational SLAs, and evolve without introducing instability or uncontrolled cost .This is a production operations role, focused on runtime behavior, infrastructure, and reliability . What You’ll DoDesign, deploy, and operate end‑to‑end production ML pipelines across Dev, QA, and Prod environment s.Set up and manage AWS SageMaker pipelines, endpoints, and monitoring for large scale inference workloads, including embedding generation, named entity recognition, reranking, and video processin g.Own GPU and CPU infrastructure selection, scaling, and optimization, including instance benchmarking, autoscaling behavior, and load testin g.Deploy, monitor, and operate inference services that support hundreds of thousands of queries per day across text, image, and video pipeline s. Required Skills & Experie nceHands‑on experience deploying and operating ML inference systems in producti on.Strong experience with AWS SageMaker, including pipelines, endpoints, monitoring, and multi‑environment deploymen ts.Expertise deploying ML models using PyTorch and TensorFlow from an operational and serving perspecti ve.Proven experience with model deployment and orchestration, including containerized inference and autoscali ng.Experience selecting, evaluating, and optimizing compute resources (GPU/CPU) for production ML workloa ds.Experience setting up monitoring, evaluation metrics, and A/B testing frameworks for ML systems in producti on.Ability to collaborate effectively with ML Engineers, Data Scientists, and platform teams in a shared ownership model. Show more Show less