Infrastructure
110 bites tagged Infrastructure — interview questions with model answers, and 60-second explainers.
How do you manage secrets for hundreds of services in centralized CI/CD?
It tests secret sprawl prevention and least privilege in CI/CD. Answer: use a secrets manager with RBAC, short-lived credentials, runtime injection, and audit logs. Red flag: secrets in Git, plain env vars, or one shared master key.
Canary vs shadow deployments: use cases and requirements
This tests whether you distinguish user-facing rollouts from invisible duplication. Canary routes some real users to new code to limit blast radius; shadow mirrors traffic to an isolated clone to test performance without user impact.
Rolling vs blue/green deployments: differences and trade-offs
Tests risk-cost-downtime judgment. Contrast rolling's gradual swap with blue/green's parallel swap; rolling is cheaper but mixes versions, while blue/green doubles capacity for instant rollback. Red flag: saying blue/green cheaper or rolling double-capacity
Define configuration drift in IaC. How do you detect and remediate it?
This tests state divergence between declared and live infrastructure. A strong answer defines drift as deviation from the IaC source of truth, proposes automated scanning for detection, and recommends reconciliation or redeployment.
Compare ephemeral container agents versus persistent build agents
Ephemeral agents ensure clean state but add cold-start latency; persistent agents speed builds via caching yet risk config drift. Tradeoffs between isolation and speed.
Vault: Centralized Secrets with Dynamic Leasing
Vault is a secrets firewall: it centralizes credentials and issues short-lived leases instead of static keys. Use it when apps need DB passwords not hardcoded. The footgun is using Vault without audit logs, leaving secrets unmonitored.
N+1 Redundancy: One Spare for the Whole System
N+1 redundancy is like having one spare tire for your whole car. You have N active components and one shared, passive backup. It's used in server racks or power supplies for high availability without doubling costs.
Declarative vs. Imperative Automation
Declarative automation defines the desired end state (“what”), not the steps to get there (“how”). It's used in tools like Kubernetes to manage complex infrastructure, letting the system figure out the details.
MLOps: When to Build vs. Buy Your Infrastructure
Deciding to build or buy MLOps tools hinges on whether it creates a competitive advantage. For commodity tasks like experiment tracking, buying a managed service avoids locking up engineers.
TensorFlow Serving: A Production Server for ML Models
Think of TensorFlow Serving as a dedicated web server for your ML models. It provides a stable API for inference and manages model versions, abstracting away deployment complexity. The main footgun is thinking it only serves models; it serves any 'Servable'.
Slash Your Cloud Bill by Taming Data Egress Costs
Data egress is the tax for moving data out of a cloud provider's network, a common cost in MLOps when moving models or datasets. To save money, keep compute and data in the same region. The footgun is forgetting that traffic between regions also counts.
Cloud Cost Anomaly Detection: Finding Waste
Think of it as a smoke detector for your cloud bill, distinguishing 'good' growth-related costs from 'bad' waste. It automatically flags unexpected spending spikes from misconfigurations or bugs.
Reserved Instances vs. Savings Plans: Pre-pay for Cloud Discounts
Think of Reserved Instances and Savings Plans as buying cloud compute in bulk for a discount. You commit to a certain usage level for 1-3 years to save money on steady-state workloads like production databases.
Data Storage Tiering: Pay Only for the Access You Need
Treat data like items in a house: hot, frequently used data on the counter; cool, less-used data in the pantry. Cloud providers use this to price storage, letting you move old logs to cheaper tiers.
Stop Paying for Idle Cloud Resources
Stop paying for idle cloud servers. Automated shutdown is like turning off the lights in an empty office, running compute only when needed. It's ideal for dev environments or scheduled batch jobs. The footgun is applying this to stateful production services.
GPU Utilization: Are You Wasting Your Most Expensive Resource?
GPU utilization isn't just a percentage; it's a measure of your return on investment. It tells you if your expensive hardware is computing or just waiting for data. Use it to diagnose slow training jobs and right-size cloud instances for ML workloads.
Showback vs. Chargeback: Who Pays for Compute?
Showback tells teams what their resource usage costs; Chargeback makes them pay for it. It's the difference between a receipt and a bill. These models help manage cloud costs, but implementing chargeback without granular tracking leads to disputes.
Cloud Pricing: On-Demand, Reserved, and Spot Instances
Cloud pricing is like booking a flight. Pay full price for flexibility (On-Demand), get a discount for committing (Reserved), or bid on empty seats for a huge discount but risk getting bumped (Spot). This choice dictates your infrastructure cost.
Cloud Cost Allocation: Making Teams Own Their Spend
Cloud cost allocation answers "who pays for what?" by assigning every dollar of your cloud bill to a team or project. It uses metadata like tags and account structures to create showback reports.
RBAC for MLOps: Who Can Do What?
RBAC assigns permissions to roles, not people. You create roles like 'Data Scientist' with specific permissions (e.g., access training data), then assign users to that role.
Hybrid Cloud MLOps: Train Anywhere, Deploy Everywhere
Treat your ML infrastructure like your applications—a consistent platform that runs anywhere, avoiding siloed stacks for data science and app dev. Use it to train on cloud GPUs but deploy on-prem for low latency, ensuring dev/prod parity across environments.
Compute Abstraction Layer: Run Code Anywhere
A Compute Abstraction Layer is a universal adapter for your code, letting you run it on a laptop, cloud GPU, or cluster without changes. It's used in MLOps to scale a script from local debug to production training. The footgun is a leaky abstraction.
The MLOps Maturity Model: A Roadmap for Growth
The MLOps Maturity Model is a roadmap from manual chaos to automated ML systems. Use it to assess your team's current state and plan incremental improvements.
Azure Machine Learning: A Service on Microsoft's Cloud
Microsoft Azure is a general-purpose cloud platform for building applications. It provides the global infrastructure and tooling support upon which specialized services, like Azure Machine Learning, are built.
Get Infrastructure bites daily.
Five a day, five minutes, offline. With quizzes so it sticks.
Open testing — you’ll join as an early tester.