MLOps / Cloud Deployment Engineer

About EviSmart™

EviSmart™ is transforming modern dentistry with AI-powered CAD generation and mesh editing solutions. Trusted by dental labs and clinics in over 26 countries, our mission is to make dental care smarter, faster, and more efficient through advanced technology that connects dentists, labs, and manufacturers worldwide.

About the Role

We are looking for an MLOps / Cloud Deployment Engineer to deploy, scale, and optimize our AI-powered platform for cloud inference. You’ll own the cloud integration process — from containerizing AI modules to configuring GPU-enabled inference servers — ensuring the system can serve multiple users efficiently and cost-effectively. This role blends engineering expertise with cloud architecture and operational best practices.

What You’ll Do

• Containerize FastAPI backend and AI modules to create reproducible environments for inference and preprocessing pipelines.
• Set up CI / CD workflows (GitHub Actions, GitLab CI, or similar) for seamless deployment.
• Deploy backend services to cloud platforms (AWS, GCP, or Azure) using Cloud Run, ECS Fargate, Kubernetes, or similar technologies.
• Configure autoscaling, load balancing, and secure API endpoints for robust, scalable performance.
• Manage GPU-enabled instances for efficient AI inference.
• Integrate object storage (S3 / GCS) and databases (PostgreSQL / MongoDB) for model weights, user uploads, and job tracking.
• Implement asynchronous processing pipelines (Celery / Redis / PubSub) to optimize GPU utilization.
• Monitor runtime performance, logging, and uptime using tools like Prometheus or Grafana.
• Analyze cloud costs and performance, recommending optimizations and long-term architecture improvements.
• Ensure secure data handling, HTTPS configuration, and compliance with privacy best practices.

What We’re Looking For

Nice-to-Have

Configured storage and database backends.

Why Join Us?

Excited to optimize AI systems for real-world impact? Apply now and share your experience deploying and scaling AI platforms in the cloud.

#J-18808-Ljbffr