Agent interviews keep returning to eight topics: the agent loop, structured output, function calling, large tool sets, memory, design trade-offs, MCP versus A2A, and prompt caching. This post strings them into one line (concept, mechanism, how to answer) and corrects when the 2026-07 MCP spec changes actually landed.
Four system design questions that come up often (enterprise RAG, an LLM serving stack, a customer-support agent, online A/B testing with a data flywheel), three Python problems (dynamic batching, sampling, backoff retries plus a token bucket), and a STAR skeleton for behavioral rounds. Each design question has a speakable answer and a self-check list, and all code was actually run.
Seven LLM engineering topics that come up often in interviews: LoRA/QLoRA and fine-tuning vs RAG, RLHF/DPO/GRPO alignment, inference optimization (PagedAttention gives vLLM 2-4x throughput), sampling and decoding, LLM evaluation, the OWASP LLM Top 10 (2026 edition), and hallucination. Each section covers the concept, the mechanism, and how to answer.
Interview follow-ups usually land on mechanisms: why divide by √d_k, how AdamW differs from Adam plus L2, why a high AUC still isn't shippable. This post walks through concept, mechanism and how to answer, then ends with 3 runnable numpy exercises.
Prompt engineering shapes a single instruction, context engineering decides what the model sees right now, and harness engineering wraps the whole non-deterministic system. Bsharat's 26 principles, Breunig's four context failures, and OpenAI's roughly one-million-line, zero-handwritten-code harness experiment each map to one layer. Evaluation is the piece teams skip most, and it belongs in a CI gate that blocks silent regressions.
Answer RAG interview questions in four steps: the three-stage pipeline, where each stage fails, which of nine variants patches which hole, and the 6 kinds of problems RAG cannot solve. Self-RAG, CRAG and Adaptive-RAG add judgment; Graph RAG and KG-RAG change the index; CAG skips retrieval; Agentic RAG and Reasoning RAG hand decisions to the model.
Read each company's own interview guidance first: Meta now expects candidates to use a built-in AI assistant, while Anthropic defaults to no AI. For question banks, pick ones that cite sources and are still maintained this year, such as the alexeygrigorev field guide, ombharatiya, and alirezadir. Only 2 of the 12 popular repos link sources for their questions, and some keep answers behind a paywall.
Behavioral interviews aren't about improvisation — they're about a pre-prepared story library. AI Engineer behavioral interviews have unique focus areas: AI ethics (bias, fairness, privacy), technical decision impact narratives (why you chose this model/architecture), and experience driving ML projects across teams. Strategy: build 8-10 STAR stories, practice each until you can deliver it in under 2 minutes.
AI Engineer coding interviews aren't identical to SWE — beyond LeetCode medium, you'll face ML-flavored problems (implementing a tokenizer, writing a batch inference pipeline, handling sparse matrices). Strategy: practice LeetCode medium to 70% pass rate, then spend remaining time on numpy/pandas operations, data processing pipelines, and ML-related programming problems.
Deep learning interviews don't ask you to derive backpropagation — they test whether you can explain the design intuition behind architectures. High-frequency topics: CNN's locality and translation invariance, why the evolution from RNN to Transformer was necessary, self-attention computation and complexity, BatchNorm vs LayerNorm use cases, and common training tricks (learning rate scheduling, gradient clipping, mixed precision).
LLM Application Design is the hottest new interview topic in 2025-2026. Key focus areas: RAG pipeline chunking/retrieval/reranking design, agent tool-use and planning loops, context window management strategies, guardrails and safety design, and LLM application evaluation methods. Interviewers especially value whether you've hit real-world pitfalls.
ML fundamentals interviews don't test formula memorization — they test whether you can explain concepts intuitively and hold up under follow-up questions. High-frequency topics: the practical meaning of bias-variance tradeoff, the selection logic for L1/L2 regularization, why cross-entropy beats MSE for classification, SGD vs. Adam tradeoffs, and how precision/recall priorities differ by scenario.
The core of ML System Design interviews isn't choosing the model — it's how to turn a business objective into a system that's deployable, monitorable, and iterable. Interviewers want to see if you can: translate business goals into ML objectives, design data pipelines and feature stores, choose reasonable serving strategies, and plan monitoring and A/B testing.
MLOps interviews test whether you have experience pushing models to production. Key topics: ML pipeline CI/CD (how it differs from software CI/CD), model registry and version management, A/B testing design and pitfalls, inference scaling strategies (horizontal scaling, model compression, caching), and production monitoring and alerting design.
The dividing line in LLM interviews is whether you've actually used these things. High-frequency topics: BPE tokenization logic and multilingual challenges, pretraining objectives (CLM vs MLM), three levels of fine-tuning (full/LoRA/prompt tuning), RLHF workflow and failure modes, prompting as engineering practice, and the difficulty of LLM evaluation with current methods.
AI Engineer interviews go beyond ML — big tech emphasizes system design and coding, startups look for end-to-end delivery, and AI-native companies test LLM engineering depth. Strategy: identify your target company types first, then allocate prep time across six dimensions (ML fundamentals, system design, LLM applications, coding, paper reading, and behavioral).
Paper reading interviews don't test whether you've read that specific paper — they test whether you can quickly understand a new method and identify its limitations. AI-native companies (Anthropic, OpenAI) particularly favor this format. Strategy: practice reading a paper in 30 minutes and verbally stating contribution + limitation, build your own must-read list, and practice summarizing each paper in three sentences.
AI Product Design is the hottest new interview topic in 2025-2026. Core areas: when to use AI (not every problem needs it), human-in-the-loop design patterns (when to let humans intervene), trust building (how to make users believe AI output), AI product challenges (hallucination, latency, cost), and AI product evaluation metrics.
Product Builder behavioral interviews differ from SWE — they don't just test teamwork, they specifically test how you drive things without formal authority. Core skills: influence narratives (how to convince engineers to build your feature), conflict resolution (disagreements with designers/engineers/stakeholders), vision expression (how to make someone understand your product direction in 30 seconds), and failure stories (learning from failure without deflecting blame).
Execution interviews test whether you can turn ideas into deliverables. Core skills: roadmap planning (how to prioritize with limited resources), priority defense (why A before B), cross-team collaboration (how to drive engineering and design), stakeholder management (how to handle conflicts), and the ability to track progress with data.
Growth interviews don't test whether you can growth hack — they test whether you have systematic growth thinking. Core skills: growth loop design (the acquisition → activation → retention → referral flywheel), experiment design (the full hypothesis → metric → experiment → analysis process), retention strategy (finding the aha moment, designing habit loops), and using data to decide what's worth continued investment.
Metrics interviews test whether you can make decisions with numbers, not how much statistics you know. Core skills: north star metric selection logic (why this one and not that one), metric tree decomposition (finding actionable levers), funnel analysis (which step's drop-off is most worth fixing), A/B testing design and pitfalls, and judgment when facing counterintuitive data.
A Product Builder isn't a traditional PM — you need to build from 0 to 1, not just write PRDs. Interviews test the intersection of product intuition, metrics thinking, technical understanding, and execution ability. Prep strategy: first figure out whether your target company wants a PM or a Builder, then allocate time across nine dimensions.
Product Design interviews don't test whether you can draw wireframes — they test how you go from problem to solution. Core skills: MVP scope judgment (what to build and what not to), trade-off analysis (speed vs completeness, generic vs custom), communication of design decisions (why A instead of B), and iterative thinking.
Product Sense interviews don't test how many features you can think of — they test whether you can find the problem truly worth solving within a vague requirement. Core skills: user segmentation thinking, problem reframing (turning 'add a feature' into 'what problem are we solving'), structured reasoning for feature prioritization, and the ability to hold or revise your judgment under follow-up questions.
Strategy interviews don't test whether you can recite frameworks — they test whether you can make judgments with incomplete information. Core skills: market sizing (the practical use of TAM/SAM/SOM, not rote numbers), competitive moat analysis (network effects, switching costs, brand), go/no-go decisions for new markets, and using elimination rather than addition for strategic trade-offs.
Technical PM interviews don't require you to write production code, but you need to be able to read trade-offs. Core skills: API design fundamentals (RESTful, versioning, error handling), high-level system architecture understanding (microservices, database selection, caching), collaboration patterns with engineers (RFC process, technical spec review), and making product decisions under technical constraints.