Prerequisites
- Cloud fundamentals and basic programming knowledge
- 30-60 minutes of study time per day
- Optional AWS account for SageMaker and data service walkthroughs
Study Schedule
Month 1 (Days 1-30)ML and Data Foundations
- Week 1: ML basics, supervised/unsupervised learning, metrics, and model lifecycle
- Week 2: S3, data formats, partitioning, and dataset organization
- Week 3: Glue, Athena, DataBrew, and SageMaker Processing
- Week 4: Feature engineering, Feature Store, data quality, and Domain 1 practice
Month 2 (Days 31-60)Model Development and SageMaker
- Week 5: SageMaker training jobs, built-in algorithms, and custom containers
- Week 6: Hyperparameter tuning, distributed training, and cost optimization
- Week 7: Model evaluation, registry, versioning, and approval workflows
- Week 8: Domain 2 practice, flashcards, and missed-answer review
Month 3 (Days 61-90)Production ML Operations
- Week 9: Inference modes, endpoint deployment, variants, and autoscaling
- Week 10: SageMaker Pipelines, CI/CD, IaC, and MLOps workflow orchestration
- Week 11: Model Monitor, CloudWatch, drift, troubleshooting, IAM, KMS, and VPC endpoints
- Week 12: Two full mock exams, weak-domain review, and final flashcards
Study Tips
Pair theory with console walkthroughs for SageMaker jobs, endpoints, pipelines, and monitoring.
Treat each wrong answer as a cue: metric selection, service selection, workflow order, or security control.
Review official domain weights weekly so your study time matches the exam shape.
Keep the final week focused on recall and scenario recognition, not brand-new topics.
Ready to Practice?
Put your study plan into action with MLA-C01 practice questions.