Experience deploying and orchestrating ML/LLM workloads on AWS Bedrock or SageMaker.
Proficiency with AWS services used in ML pipelines: Lambda, API Gateway, ECR, S3, Step Functions.
Ability to containerize and deploy ML components using Docker.
Experience integrating vector databases or retrieval components within AWS environments.
Strong understanding of automation, service orchestration, and model-runtime integration on AWS.
Experience with CloudWatch for observability.
Integrating LLM/RAG pipelines with AWS-managed services end-to-end.
Familiarity with CI/CD tooling (GitHub Actions, AWS CodeBuild/CodePipeline).
Cost-awareness when running model endpoints and retrieval workflows.