MLOps Engineer ID72409

AgileEngine • Berwyn, IL

5d • Hybrid

About The Position

AgileEngine is seeking an MLOps Engineer to deploy, scale, and monitor computer vision models in production on Azure, processing real-time image streams from thousands of edge cameras. The role is based in or requires relocation to Dallas, Texas, with office attendance three days per week; the posting also describes flexible scheduling and remote and office options.

The engineer will own the transition from AI/ML experimentation to reliable production deployments, build and maintain high-volume image ingestion and inference pipelines, and manage cloud-based inference environments. The role focuses on optimizing GPU efficiency and infrastructure costs, monitoring model and system performance, and managing model tracking and versioning. The engineer will also collaborate with data scientists and AI researchers to turn experimental models into production-ready solutions, with secondary support for select edge GPU deployments.

Requirements

• At least 3 years of professional experience in MLOps, DevOps, Data Engineering, Machine Learning, or Software Engineering.
• Degree in Computer Science, Software Engineering, or a related technical discipline, or equivalent practical experience.
• Must be authorized to work for any employer in the United States; the company cannot sponsor or take over employment visa sponsorship.
• Must be based in Dallas, Texas, or be open to relocating there; office attendance is required three days per week.
• Experience with production model serving using Triton Inference Server, TorchServe, KServe, or Azure ML endpoints behind REST/gRPC APIs, and end-to-end backend pipeline ownership.
• Exposure to experiment tracking, model registry and versioning, drift detection, and production telemetry and monitoring.
• Working exposure to computer vision or image data in production.
• Practical cloud experience focused strictly on Azure, including AKS, Azure DevOps, the Azure data stack, and managing or provisioning GPU compute resources.
• Strong understanding of containerization, such as Docker and Kubernetes, and designing robust CI/CD pipelines for automated deployments.
• Conceptual understanding of AI/ML fundamentals sufficient to communicate, troubleshoot, and collaborate with applied model developers.
• Upper-intermediate English proficiency.

Responsibilities

• Optimize GPU compute efficiency and infrastructure costs, including maximizing camera throughput per GPU.
• Apply model and inference optimization techniques such as FP16/INT8 quantization, pruning, TensorRT/ONNX conversion, dynamic batching, and GPU autoscaling on AKS.
• Own the lifecycle transition from AI/ML experimentation to reliable, high-performance production deployment.
• Build, maintain, and scale ingestion and inference pipelines for high-volume image streams using Azure Data Factory, cloud storage, and automated CI/CD workflows.
• Architect and manage large-scale cloud-based model inference environments, with secondary support for specific edge GPU use cases.
• Implement production monitoring, visibility dashboards, and data and concept drift detection to support model accuracy and system reliability.
• Manage experiment tracking and model versioning to provide reproducibility and traceability for production models.
• Collaborate with data scientists and AI researchers to translate experimental models into robust production-ready solutions.

Benefits

• Mentorship, TechTalks, and personalized growth roadmaps.
• USD-based compensation with education, fitness, and team activity budgets.
• Flexible schedule with remote and office options.
• Opportunity to work on modern solutions with Fortune 500 and top product companies.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level