You will own the deployment and management of scalable infrastructure for generative AI solutions on AWS.
Responsibilities
- Deploy LLMs on AWS Bedrock using boto3 for scalable inference.
- Manage SageMaker pipelines for LLM fine-tuning using EKS and Auto Scaling.
- Configure CI/CD pipelines using GitlabCI and Terraform.
- Set up Retrieval Augmented Generation (RAG) infrastructure with AWS OpenSearch and langchain within VPCs.
- Deploy AI agents (crewai/autoegen) on AWS Lambda integrated with n8n.
- Orchestrate container deployments using Docker on Amazon ECS/EKS with Kubernetes.
- Manage networking, including Route 53 and NAT Gateway, ensuring secure access.
- Monitor infrastructure health using Amazon CloudWatch and wandb.
Required Skills
- 5+ years of DevOps experience with AWS and AI workflows.
- Expertise in AWS Bedrock, SageMaker, EC2, VPC, Route 53, NAT Gateway, and Auto Scaling.
- Proficiency in Terraform, Docker, Kubernetes, langchain, and n8n workflows.
- Experience configuring CI/CD with GitlabCI and CodePipeline/CodeBuild.
- Strong command of AWS services including ECS and EKS.
Preferred Skills
- AWS certification (DevOps Engineer or Solutions Architect).
- Familiarity with llamaindex and n8n templates.