Portfolio ↗

Quiz

2988 questions of the kind that actually get asked — in interviews, in architecture review boards, and by the person who has to run the thing at 3 AM. Every answer states the trade-off rather than the slogan, and says when the obvious choice is the wrong one.

All areas2988 Architecture Fundamentals91 Distributed Systems111 Data Architecture100 Cloud Architecture97 Networking96 API & Integration Architecture97 Reliability & Resilience99 Observability92 Performance & Capacity Engineering100 Security Architecture105 Cost Architecture & FinOps102 Business Architecture103 Architecture Communication102 Enterprise Architecture100 Legacy Modernization102 AI-Era Architecture106 Software Architecture & Engineering93 Architecture Patterns94 Architecture Decision-Making101 The Architect's Meta-Skills102 Delivery & Release Engineering103 Platform Engineering & Developer Experience102 Testing & Quality Architecture102 Data Platform Architecture98 Streaming & Real-Time Data103 Data Governance & Semantics91 Frontend & Experience Architecture101 Edge, Mobile & IoT98 Regulatory & Data Protection Architecture99 Assurance, Audit & Model Risk98
Difficulty Any beginner intermediate advanced

4 questions in LLM Application Architecture.

  1. LLM Application Architecture advanced

    A workspace product adds AI features over user content. Which architectural decisions dominate, and which are commonly deferred at cost?

    2 min answer llm-applicationpermissionslatencycaching
  2. LLM Application Architecture advanced

    An LLM chat product serves millions of multi-turn conversations. How do KV-cache reuse, prefix caching, continuous batching and session affinity change the architecture, and what breaks when a session lands on a different GPU?

    3 min answer character-aikv-cacheprefix-cachinginference
  3. LLM Application Architecture advanced

    The vLLM paper on PagedAttention (SOSP 2023) reports 2 to 4 times the throughput of the then state-of-the-art serving systems at the same latency, with larger gains for longer sequences and more complex decoding, from managing the key-value cache in fixed-size blocks like operating-system pages rather than as one contiguous per-request reservation. Its profiling of existing systems found only roughly 20 to 38% of key-value cache memory holding actual token state. What was the real constraint, what did the change buy, and where would copying the lesson be a mistake?

    3 min answer kv cachepaged attentionmemory fragmentationbatching
  4. LLM Application Architecture advanced

    Zoom publicly describes the architecture behind its AI Companion as a federated approach - its own models used alongside third-party frontier models, with work routed by task rather than every request going to a single provider. What problem does that structure solve that a single-provider design does not, and where would copying it be a mistake?

    3 min answer model-routingmulti-providercostevaluation