Job Description
We are looking for 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 mandatory requirements are being based in Dallas, TX, or open to relocating there, availability to work onsite 3 days a week, production model serving with Triton Inference Server, TorchServe, KServe, or Azure ML endpoints, hands-on experience with computer vision or image data in production, Azure (AKS and Azure DevOps), 3+ years of experience in MLOps, DevOps, ML, or software engineering, Docker, Kubernetes, CI/CD, and an upper-intermediate English level.
WHAT YOU WILL DO
- Resource & Cost Optimization: Lead GPU compute efficiency and infrastructure cost-reduction strategies by optimizing models to maximize camera throughput per GPU. Apply optimization techniques including quantization (FP16/INT8), pruning, TensorRT/ONNX conversion, dynamic batching, and GPU autoscaling on AKS.
- End-to-End Deployment: Own the complete lifecycle transition from AI/ML experimentation to reliable, high-performance production deployment.
- Infrastructure & Pipelines: Build, maintain, and scale robust ingestion and inference pipelines for high-volume image streams using Azure Data Factory, cloud storage, and automated CI/CD workflows.
- Edge & Cloud Deployment: Architect and manage large-scale cloud-based model inference environments, with secondary support for edge GPU deployment across specific edge use cases.
- System Stability & Monitoring: Implement robust production monitoring systems, build visibility dashboards, and set up data and concept drift detection to ensure ongoing model accuracy and system reliability.
- Model Lifecycle Management: Manage experiment tracking and model versioning to ensure full reproducibility and traceability of all models in production.
- Cross-Functional Collaboration: Partner closely with data scientists and AI researchers to translate experimental models into robust, production-ready solutions.
MUST HAVES
- At this moment, we will not sponsor any new applicant for employment authorization or offer immigration support for this position (e.g. F-1 STEM OPT, F-1 CPT, J-1, E-3, O-1, or any other form of work authorization requiring immigration support or sponsorship;
- 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 based in Dallas, TX, or open to relocating to Dallas. Office attendance: 3 days/week.
- MLOps Core: Production model serving (Triton Inference Server, TorchServe, KServe, or Azure ML endpoints) behind REST/gRPC APIs, with end-to-end backend pipeline ownership. Exposure to tracking, model registry/versioning, drift detection, and production telemetry/monitoring.
- Computer Vision: Working exposure to CV/image data in production.
- Infrastructure & Cloud: Strong practical experience navigating cloud environments, strictly focused on Azure, specifically using AKS for deployment, Azure DevOps, and the Azure data stack, alongside managing/provisioning GPU compute resources.
- DevOps & Automation: Deep understanding of containerization (e.g., Docker and Kubernetes) and designing robust CI/CD pipelines for automated deployments.
- AI/ML Foundation: A solid conceptual understanding of AI/ML fundamentals to effectively communicate, troubleshoot, and collaborate with applied model developers.
- Upper-intermediate English level.
PERKS AND BENEFITS
- Professional growth: Mentorship, TechTalks, and personalized growth roadmaps.
- Competitive compensation: USD-based pay with education, fitness, and team activity budgets.
- Exciting projects: Modern solutions with Fortune 500 and top product companies.
- Flextime: Flexible schedule with remote and office options.