Cloud & AI Infrastructure Engineer — I help early-stage AI startups deploy production-grade LLM infrastructure on AWS, so their team can focus on building the product instead of babysitting deployments.
If you're shipping an AI product and need someone who can get your models out of notebooks and into a scalable, observable, cost-controlled cloud environment — let's talk.
AI Infrastructure & Orchestration
End-to-end LLM deployment pipelines — model serving, prompt orchestration,
context management, and API exposure on AWS. Built to scale from prototype to
production without a rewrite.
→ ai-orchestrator-service
Event-Driven Data Pipelines
AWS-native pipelines built on Lambda, S3, SQS, and DynamoDB with an emphasis
on idempotency, back-pressure, and fault-tolerant design. Systems that stay
correct under load and fail loudly when they don't.
→ dynamodb_prototype
Cloud-Native Backend Services
High-performance backend services in Rust and Python. Correct first, observable
second — explicit error handling and defined failure modes over happy-path
assumptions.
→ backend-service
Cloud: AWS (Lambda · S3 · SQS · DynamoDB · ECS · ECR) · GCP
AI/ML: LLM APIs (OpenAI · Anthropic) · AI orchestration · RAG pipelines
Infra: Terraform · Docker · CI/CD · event-driven architecture
Languages: Rust · Python · TypeScript
I treat infrastructure as a product, not a chore. That means:
- Systems designed for failure, not just success
- Observability and cost visibility built in from day one
- Documentation written for the engineer who inherits the system at 2am
Building an AI product and need production infrastructure? Hire me! Reach out on LinkedIn — I'm always open to talking shop.