- Strong experience in designing, building, and leading enterprise
- applications/platforms
- Deep expertise in AWS infrastructure and cloud technologies
- Strong hands-on experience with Terraform
- Exposure to AI/ML technologies (at least some practical experience is required)
- Strong leadership, communication, and stakeholder management skills
Scenario:Design an enterprise-grade AI platform on AWS that enables employees to query internal knowledge using a Retrieval-Augmented Generation (RAG) approach. The system should be secure, scalable, and compliant, leveraging AWS Bedrock for LLM capabilities.
Core Components:
- Frontend UI (EKS/ECS + ALB + SSO)
- Backend API and orchestration layer
- Hybrid knowledge layer (Vector DB + Graph DB)
- LLM inference using AWS Bedrock
- Strong security, compliance, and observability controls
Presentation Requirements:Candidates should present their solution using a (or equivalent) architecture diagram, covering:
Logical Architecture: High-level layers (UI, API, orchestration, knowledge, model, security, resiliency, availability)
Implementation Architecture: Mapping to AWS services (EKS/ECS, ALB,
Bedrock, OpenSearch, Neptune, S3, IAM, VPC, etc.)
Expectations During Discussion:
- Explain design decisions, trade-offs, and assumptions
- Demonstrate CI/CD, IaC, and platform engineering best practices
- Show end-to-end RAG data flow
- Map logical components to AWS services and networking
- Define security boundaries (VPCs, subnets, IAM roles, private
- endpoints)
- Highlight integrations (SSO, Bedrock, databases, storage)
- Address scalability (auto-scaling, stateless services, load
- balancing)
- Illustrate hybrid retrieval flow (vector + graph)
- Include observability and monitoring
- Clearly depict data flow
Never miss an opportunity! Create an alert based on the job you applied for.
