Model Deployment Courses and Certifications

Board Infinity

Cloud Platforms for ML: AWS, Azure & GCP Deployment

Deploy ML models on SageMaker, Azure ML Studio, and Vertex AI, build serverless inference with Lambda and Cloud Functions, and compare platforms on cost and scalability.

• Coursera
• 4 weeks, 5 hours a week
• Self-Paced
• Paid Course

Autoscaling TensorFlow Model Deployments with TF Serving and Kubernetes

Deploy a TensorFlow model with TF Serving on Kubernetes and configure autoscaling so prediction serving keeps up with changing request load.

• Coursera
• 1 hour 30 minutes
• Self-Paced
• Paid Course

Implementing Canary Releases of TensorFlow Model Deployments with Kubernetes and Anthos Service Mesh

Implement canary releases for TensorFlow model deployments on Kubernetes, using Anthos Service Mesh and Istio to shift traffic gradually between model versions.

• Coursera
• 1 hour 30 minutes
• Self-Paced
• Paid Course

Packt

Optimizing, Deploying, and Governing LLMs in the Enterprise

Manage the full enterprise LLM lifecycle: craft data pipelines, optimize inferencing with quantization and edge deployment, monitor models in production, and apply responsible AI practices.

• Coursera
• 7 weeks, 1 hour a week
• Self-Paced
• Paid Course

Coursera

Orchestrate, Evaluate, and Release GenAI Systems

Analyze deployment manifests for dependency conflicts, judge release readiness from regression tests and observability dashboards, and build canary workflows with automated rollbacks for GenAI systems.

• Coursera
• 3 weeks, 1 hour a week
• Self-Paced
• Paid Course

Edureka

Deploying Fine-Tuned AI Models

Deploy fine-tuned AI models to production with FastAPI, Docker, and MLflow, applying quantization and distillation, monitoring drift and versions, and evaluating fairness with model cards.

• Coursera
• 3 weeks, 2 hours a week
• Self-Paced
• Paid Course

Implementing Canary Releases of TensorFlow Model Deployments with Kubernetes and Anthos Service Mesh

In this lab you will install the Anthos Service Mesh, and deploy a resnet model, all on a GKE cluster.

• Google Skills
• 1-2 hours
• Self-Paced
• Paid Course

Amazon Web Services;  Amazon

AWS ML Engineer Associate 3.1: Seleção de uma infraestrutura de implantação (Português) | AWS ML Engineer Associate 3.1 Select a Deployment Infrastructure (Portuguese)

Aprenda a selecionar infraestruturas, estratégias de inferência e recursos computacionais para implantar modelos de ML na AWS.

• AWS Skill Builder
• 1 hour
• Self-Paced
• Paid Course

Amazon Web Services;  Amazon

AWS ML Engineer Associate 3.1 Select a Deployment Infrastructure (Simplified Chinese)

聚焦机器学习模型部署基础设施，涵盖编排服务、推理目标、容器与计算实例，以及生产和测试环境的资源配置。

• AWS Skill Builder
• 1 hour
• Self-Paced
• Paid Course

Amazon Web Services;  Amazon

AWS ML Engineer Associate 3.1 Select a Deployment Infrastructure (Korean)

ML 파이프라인의 프로덕션 및 추론 인프라를 설계하고 AWS 컴퓨팅·오케스트레이션·호스팅 옵션을 선택합니다.

• AWS Skill Builder
• 1 hour
• Self-Paced
• Paid Course

Amazon Web Services;  Amazon

AWS ML Engineer Associate 3.1 Select a Deployment Infrastructure

Select AWS production and inference infrastructure for deploying machine learning models, from orchestration and hosting strategies to compute resources and edge optimization.

• AWS Skill Builder
• 1 hour
• Self-Paced
• Paid Course

Amazon Web Services;  Amazon

AWS ML Engineer Associate 3.1 Select a Deployment Infrastructure (한국어)

AWS에서 ML 모델의 추론 인프라, 배포 대상, 컨테이너 및 컴퓨팅 리소스를 선택하는 고급 과정입니다.

• AWS Skill Builder
• 1 hour
• Self-Paced
• Paid Course

Amazon Web Services;  Amazon

AWS ML Engineer Associate 3.1 Select a Deployment Infrastructure (简体中文)

在 AWS 上选择机器学习模型部署基础设施、推理目标、容器与计算资源，涵盖生产和测试环境配置。

• AWS Skill Builder
• 1 hour
• Self-Paced
• Paid Course

Amazon Web Services;  Amazon

AWS ML Engineer Associate 3.1 Select a Deployment Infrastructure (Português)

Aprenda a selecionar infraestrutura AWS para implantar modelos de machine learning, abrangendo orquestração, inferência, contêineres, instâncias computacionais e computação de borda.

• AWS Skill Builder
• 1 hour
• Self-Paced
• Paid Course

Krish Naik

End to End Machine Learning Project Implementation with Dockers, GitHub Actions and Deployment

Build a linear-regression house-price application, expose predictions through Flask, and deploy it with GitHub Actions, Docker, and Heroku.

• YouTube
• 2 hours 45 minutes
• Self-Paced
• Free Video