AI Engineering · Agents · RAG · DevOps · Cloud
I’m Supraj Maripeddi, a Senior Cloud & Platform Engineer. This is my personal space for practical AI engineering, agents, RAG and production AI — supported by the cloud, DevOps, Kubernetes and platform systems I work with.
Latest Writing
AI engineering first — plus the cloud, DevOps and platform lessons that make production systems work.
Featured
Guardrails are the runtime control plane around an LLM — what they are, why every production AI app needs them, and how to implement them with Bedrock Guardrails, NeMo Guardrails, and Llama Guard, with real configs.
Read articleThe forward deployed engineer doesn't build for the customer — they build with them. What the role actually is, where it came from, the glue code nobody sees, and how to tell if it's you.
Read →Loop engineering is the 2026 shift from prompting AI agents turn-by-turn to designing the system that prompts, verifies, retries, and stops them. What it is, why it matters, and how to build one — with real loops.
Read →AWS Lambda MicroVMs is a new serverless primitive giving every user or AI agent its own Firecracker sandbox — VM isolation, near-instant resume, and state for up to 8 hours. Here's how it works and how to run one.
Read →Topics
Live from the topic library — 171 topics published across 9 areas so far. New entries show up here the moment they're written, no homepage edits required.
AI
compiling declarative prompt pipelines
Read the notes →SECURITY
perimeter-less access verification
Read the notes →CLOUD
containing blast radius through cells
Read the notes →Interview Prep
Scenario questions, answer structure, common mistakes and follow-up thinking. AI engineering becomes the lead direction as that library grows; cloud-native practice stays grounded in real questions already published.
Open interview prepSample Scenario · Kubernetes · Hard
Answer first. Reveal second. Compare your reasoning, not just commands.
Practice this track →Courses & Structured Learning
The course experience is being developed independently and will be integrated into supraj.dev later. This redesign keeps the website ready for that integration without duplicating or forking the course implementation here.
About
I publish what is useful when it is ready — increasingly AI engineering, backed by real DevOps, cloud, Kubernetes and platform experience.
About Supraj →