+7ML fundamentals deep dive for ML rolesML designAfter a short walk through your resume, expect fast questions on machine learning basics, usually centred on your own area (language models, vision, recommendations). For each…
Last asked Oct 2026
#llm
- +7
- Design LLM review summaries that resist prompt injection and PII leaksAI system designBuild a platform that takes customer product reviews from an online store and has a large language model summarize them for an internal dashboard. The round centered on trust and…Last asked Oct 2026
Conversation history under a token budgetCodingFit a conversation history into a token budget for the next model call, keeping the most important messages and dropping or summarizing the rest. Reported on 1point3acres' Sierra…Last asked Oct 2026
+1Design an AI prompt playgroundAI system designDesign a web workspace where developers write prompts, run them against several models and settings, compare outputs side by side, and save and share versions.Last asked Oct 2026- Design an LLM agent for production status, work orders and quotesAI system designPeople at a manufacturing business talk to an AI agent in plain language. It has to handle three kinds of request: report how far along an order or production job is, open a new…Last asked Oct 2026
Research engineering training discussionML designDiscuss training approaches for long-context and long-horizon tasks, then explore past projects, environment design and reward design with team leads. Reported on 1point3acres'…Last asked Sep 2026
Design an LLM chatbot with RL-trained answersAI system designDesign a chatbot that answers users' questions in real time, built on a large language model. Cover the serving path (latency, streaming answers, scale), then the learning loop:…Last asked Sep 2026
+1Greedy, top-k and top-p decoding for a language modelCodingYou get a toy language model with a small vocabulary whose forward pass returns next-token logits for the tokens so far. Using NumPy, write the generation loop and three ways to…Last asked Sep 2026- Replace a text game's heuristic logic with LLM callsCodingYou are handed a text game that runs in the terminal, with a few hundred lines of Python that make its decisions through hand-written rules. In a live session, swap that…Last asked Sep 2026
- Make an LLM recognize questions past its training cutoffML designChat assistants sometimes answer a question about recent events by saying their knowledge stops at a certain date. You are building an LLM: how would you get it to notice that a…Last asked Sep 2026
+5Design an AI chatbot appAI system designBuild a chatbot app on top of a hosted LLM API: conversations, streamed answers, history, and per-user usage limits.Last asked Sep 2026
Design the security architecture for an LLM chatbotAI system designA company runs a customer-facing chatbot built on a language model. Design its security: protecting the bot from abuse and prompt injection, limiting the data it can see and the…Last asked Sep 2026
Decoder-only LLM architecture and how vLLM serves itML designExplain how a decoder-only language model is built, from tokens through the stack of attention and feed-forward layers to predicting the next token. Then explain how an inference…Last asked Sep 2026- Multi-step task with an LLM tool-use loopCodingIn a notebook with docs open, solve a multi-step problem by writing code that calls a language model as a building block: design the prompts and the loop that invokes tools and…Last asked Sep 2026
Turn company policies into step-by-step support instructionsAI system designDesign a retrieval-augmented system for customer support staff: given a user's issue, it reads the company's policies and produces step-by-step instructions the agent can follow…Last asked Sep 2026
LLM application engineering: RAG, context limits, state and prompt injectionML designQuick conceptual questions for an applied AI engineer, each answered in a couple of minutes from real experience: 1. When would you use retrieval-augmented generation and when…Last asked Sep 2026
RMSNorm versus LayerNorm in a transformer blockML designWrite the formulas for LayerNorm and RMSNorm and say what each normalizes. What does RMSNorm give up by skipping the mean, why does it work about as well in practice, and why do…Last asked Sep 2026- Mixture of experts and expert parallelismML designExplain how a mixture-of-experts transformer layer works and follow a batch of tokens through it: the router, top-k selection, the all-to-all exchange that sends tokens to experts…Last asked Sep 2026
- +1Tensor parallelism versus pipeline parallelismML designA transformer is too big for one accelerator. Explain how tensor parallelism and pipeline parallelism each split it: what is cut, what crosses the wire and when, where the idle…Last asked Sep 2026
- KL divergence in language modelsML designDefine KL divergence and explain what it measures. Then explain where it is used with large language models and why, for example as a penalty that keeps a fine-tuned model close…Last asked Aug 2026
- What perplexity tells you about a language modelML designDefine perplexity and explain how to read it: what a lower or higher number means, how it relates to cross-entropy, how it is used for today's large language models, and where it…Last asked Aug 2026
- Importance sampling in LLM trainingML designExplain importance sampling: what it is and why it works. Then explain where it is used when training large language models and why it is used there. Expect to go beyond the…Last asked Aug 2026
- Detect and prevent reward hackingML designExplain reward hacking when a language model is trained with reinforcement learning: what it looks like, how you would detect it, and what you would change in the reward, the data…Last asked Aug 2026
- Design a music recommender driven by an LLM agentAI system designDesign a music recommendation product in which an LLM agent talks with the listener and suggests songs or playlists. Cover how the agent reaches the listener's history and the…Last asked Aug 2026
CSV upload endpoint that classifies rows with an LLMCodingA practical round: build a service endpoint that takes an uploaded CSV, sends each row to a language model to classify it, and returns the results as JSON. Write the prompt and…Last asked Jul 2026
Design a text-to-SQL chatbot with access controlAI system designDesign a chatbot that turns questions into SQL over internal data. Make sure users only reach data they are allowed to see, and stop invented tables, unsafe statements and runaway…Last asked Jul 2026- Rapid-fire questions on LLM internalsML designA fast round of short questions on how LLMs work: transformer and attention internals, training and fine-tuning choices, and how models are run in practice. Each answer should be…Last asked Jul 2026
- Build a RAG agent on the Mistral API, then defend its designAI system designWrite a small Python tool that answers questions over a local folder of Markdown and PDF files with retrieval-augmented generation: ingest and chunk the files, embed and index the…Last asked Jul 2026
- Design an LLM-based coding assistantAI system designDesign an AI coding assistant that helps developers inside their editor: completing code, answering questions about a codebase and making edits on request. Discuss how it gathers…Last asked Jun 2026
Manage the context window in an applied LLM systemAI system designAn applied AI product keeps hitting the model's context limit. How do you decide what goes into the context on each call? Discuss retrieval, trimming and summarizing history…Last asked Jun 2026- LLM foundations: architecture, adaptation and steeringML designA broad conversation on large language models: how the architecture works, the ways to adapt a model to a task (full fine-tuning, parameter-efficient methods, prompting), and the…Last asked Jun 2026
- GRPO deep dive for a reasoning LLMML designExplain GRPO and why it can drop the critic that PPO uses. Then discuss the parallelism used to train a reasoning language model, multi-head latent attention (MLA), and how you…Last asked Jun 2026
- Tokenizer design and KL-regularized fine-tuningML designDiscuss how you would design a tokenizer for a language model and the trade-offs involved. Then explain supervised fine-tuning with a KL penalty that keeps the model close to its…Last asked Jun 2026
Design a system that turns Jira tickets into pull requestsAI system designDesign an automated system that picks up a Jira ticket, uses an AI coding agent to write the change in the right repository, and opens a pull request for review. Cover how tickets…Last asked Jun 2026
Speed up object-backed APIs, then design LLM observabilityAI system designTwo parts. First, make slow API endpoints whose data lives in stored objects faster. Then design an observability platform for LLM applications: capturing traces of model calls…Last asked Jun 2026
Design a multi-agent document search and visualization productAI system designDesign a product in which several AI agents work together to search a large collection of documents and present what they find visually. Cover how the work is split among agents…Last asked Jun 2026- Design an LLM chat over SEC filingsAI system designDesign a chat assistant that answers analysts' questions from SEC filings. Cover ingesting and parsing the filings, chunking and indexing long documents with tables, retrieval…Last asked Jun 2026
- Evaluate noisy data for LLM post-trainingML designYou have data collected for post-training a language model and some of it is noisy. How would you measure its quality, find the bad examples, and decide what to keep, fix or drop…Last asked May 2026
Design personalization memory for a chatbotAI system designDesign how an AI assistant remembers things about each user across conversations and uses them to personalize answers. Cover what to store and how it is extracted, retrieval at…Last asked May 2026- Design per-user model usage quotas for a mobile appSystem designDesign how a mobile app enforces per-user quotas on model usage: how usage is counted, where the limit is enforced, what the app shows the user as they approach and reach it, and…Last asked May 2026
- Design an agent harness and its evaluation systemAI system designDesign the harness that runs an AI agent (the loop that calls the model, runs its tools and manages its context) together with the system that evaluates it. Cover how the agent…Last asked Apr 2026
- Mechanistic interpretability experiment on double descentML designDesign and run a small-model experiment reproducing sample-aspect double descent, explain the phenomenon from theory, and propose a remedy. The deliverable is the experiment plus…Last asked Apr 2026
- +5Design a RAG system over company docsAI system designEmployees should be able to ask questions about internal documents (Drive, Confluence, Slack, GitHub) and get grounded answers with citations.Last asked Mar 2026
- Design an AI agent rollout for a global enterpriseAI system designA forward-deployed engineering design round. A large global company wants to adopt AI agents across its business. Design the agent and how it gets rolled out: which work it takes…Last asked Mar 2026
- Debug a GRPO training script and defend the RL mathML designBelow is a small group relative policy optimization (GRPO) trainer in plain Python. The policy is a table of logits per prompt, and the reward is the share of tokens that match…Last asked Mar 2026
- Design an AI gatewayAI system designDesign a gateway that sits between a company's services and the language-model providers they call. Cover routing requests across providers and models, failover, rate limits and…Last asked Feb 2026
- Design a real-time AI voice agentAI system designDesign a system in which callers talk to an AI agent over the phone or in an app in real time: speech recognition, the language model, speech synthesis, keeping the response delay…Last asked Feb 2026
- LLM fine-tuning and generative modelsML designExplain how large language models are fine-tuned: supervised fine-tuning, parameter-efficient methods such as LoRA, and preference tuning, with the trade-offs of each. Then…Last asked Feb 2026
- Design guardrails and fallbacks for a reliable LLM serviceAI system designA product depends on calls to a large language model. Design the guardrails and fallback paths that keep it reliable: what you check on the way in and on the way out, what the…Last asked Feb 2026
- Design a chatbot over structured and unstructured company dataAI system designDesign an assistant that answers employees' questions from two kinds of sources: tables in databases and documents. Cover how a question is routed (query generation for tables…Last asked Feb 2026
- Design a multi-agent chat backendAI system designThe interviewer demos a ChatGPT-style product, then asks you to design its backend: a harness in which several agents work on one user request. Cover how a request is planned and…Last asked Feb 2026
- Prompt design with evaluation scaffoldingML designIn a notebook, design prompts for a defined task and write the surrounding scaffolding that evaluates them. The exercise tests task framing and measurement more than clever…Last asked Jan 2026
Post ingestion and LLM scoring pipeline take-homeCodingOver a few hours, build a small pipeline that loads a public dataset of social posts, validates each record against a schema, stores them locally, and runs a worker that sends…Last asked Jan 2026
Design a grounded voice assistantAI system designDesign a voice assistant whose answers are grounded in trusted sources rather than made up. Cover speech recognition, understanding the request, retrieving the right information…Last asked Jan 2026- Design a computer-use agentAI system designDesign an agent that operates a computer the way a person does: it looks at the screen, decides the next action and clicks or types until a task is done. Cover how the model…Last asked Jan 2026
- Shard a large input embedding table across devicesML designA model's V, H input embedding table is too big for one device. Compare sharding along the vocabulary with sharding along the hidden dimension: how a lookup works in each, the…Last asked Jan 2026
- Shard an LM head and combine the logitsML designThe output layer maps a hidden state through an H, V weight matrix to vocabulary logits. Compare splitting the weight by vocabulary with splitting it by hidden dimension: what…Last asked Jan 2026
- Build a text summarization API serviceCodingWith an AI assistant available, build a small production-style web service with FastAPI: POST /summarize takes JSON {"text": ...} and returns {"summary": ...}. Add input…Last asked Jan 2026
Build a recommender, then a chatbot on top of itAI system design1. Build a recommendation system from scratch: data, candidate generation, ranking, evaluation and serving. 2. Now that it exists, build a conversational interface on top of it…Last asked Jan 2026- Make LLM output match a word processor's formattingAI system designA writing assistant inside a word processor generates text that must fit the document's formatting: styles, headings, lists, tables. Design how you get the model to produce…Last asked Jan 2026
- Design an LLM chatbot: training data, rewards and deploymentAI system designDesign a chatbot built on a large language model and walk through its whole lifecycle. Go deep on three areas: how you build the training data (sources, filtering, labeling), how…Last asked Jan 2026
- Transformers and the challenges of deploying LLMsML designExplain how a Transformer works, then discuss recent advances in large language models, how you would apply one in the team's product, and the main problems with deploying LLMs in…Last asked Dec 2025
- Improve an LLM's reasoning on a domain taskML designA model reasons poorly on one specialized task. How would you improve it? Compare the options, from prompting and retrieval to fine-tuning and reinforcement learning, say what…Last asked Dec 2025
- Explain LLM training, reinforcement learning and evaluationML designWalk through how a large language model is trained, from pretraining to fine-tuning, where reinforcement learning comes in after that, and how you evaluate the model at each…Last asked Dec 2025
- Improve a chatbot's answers to questions it doesn't knowAI system designUsers ask a ChatGPT-style assistant questions it does not know the answer to. Design how the system notices these questions and gives better answers to them: what it does instead…Last asked Dec 2025
- Design a multimodal RAG assistantAI system designDesign an assistant that answers questions using retrieval over inputs of several kinds (text documents, images, tables or diagrams). Cover ingesting and embedding each kind, the…Last asked Dec 2025
- Design an LLM output quality validation systemAI system designDesign a system that checks the quality of a language model's answers before and after they reach users. Cover what "quality" means for the product, automatic checks and…Last asked Dec 2025
- How would you prevent hallucinations in an LLM-based system?ML designA screening question: how do you keep an LLM-based system from making things up? Cover grounding the model with retrieval and citations, constraining outputs, checking answers…Last asked Nov 2025
- Vision encoders and LLM bottlenecksML designExplain how vision encoders work and how they are trained, then the main performance bottlenecks of large language models (memory, latency) and how to reduce them.Last asked Nov 2025
- Design a large-scale MoE pretraining pipelineML designDesign the training setup for pretraining a mixture-of-experts language model across many GPUs. Cover how experts and other layers are parallelized, token routing and load…Last asked Sep 2025
- Design an asynchronous RL post-training systemML designDesign a system for post-training a large language model with reinforcement learning where generation (rollouts) and training run asynchronously. Cover how rollout workers and…Last asked Sep 2025
- Design the front end of a desktop AI chat appSystem designDesign the client side of a desktop chat app for an AI assistant: the conversation list, the chat view and the model's replies as they stream in. This is a front-end system design…Last asked Sep 2025
- Design a RAG system end to endAI system designDesign a retrieval-augmented generation system from documents to answers: ingesting and chunking documents, embeddings and the index, retrieval and reranking, the prompt to the…Last asked Sep 2025
LLM provider pool with failoverCodingWrite a client that sends completion requests to a pool of external LLM providers. It should be able to switch between providers, and when one goes down, move traffic to another…Last asked Aug 2025- Design a retrieval-augmented generation systemAI system designDesign a RAG system: users ask questions and an LLM answers using documents retrieved from your corpus. Cover ingestion and chunking, embeddings and the index, retrieval and…Last asked Aug 2025
Solve math questions with an LLM: tools and chainsAI system designHow would you build a system that answers math questions such as "what is 4 + 5?" or "what is the sum of 1 to 100?" with an LLM? Discuss when to let the model answer directly…Last asked Jul 2025
Dense versus mixture-of-experts at fixed computeML designWith a fixed activated-parameter budget, compare a dense model against a mixture-of-experts on training cost, memory, communication, stability, inference and engineering effort…- RLHF take-home aligning a small open modelCodingA take-home over a few days: align a small open model with preference data and a parameter-efficient adapter on a single GPU, push the result to the Hugging Face Hub, and write up…
+1Speculative decoding for faster generationCodingImplement speculative decoding: a small draft model proposes tokens and the large model verifies them, accepting matching runs to save forward passes. Reported on 1point3acres'…- Design review: an eval gate for model launchesML designYou are reviewing the design of the evaluation gate that decides whether a new model checkpoint can launch. Critique it: what it can miss, how it can mislead, what you would…
- Group prompts into templates under concurrent ingestionCodingAn API receives prompts from many threads. Most come from a few templates filled with different values: Summarize ticket 48213 for alice@acme.com and Summarize ticket 1007 for…
Agentic RAG take-home projectCodingA take-home: build an agentic retrieval-augmented pipeline. A model with a search tool must answer questions over a document set, including questions that need more than one…- +3Evaluate a new LLM before launchML designYou have a new model checkpoint. Design the evaluation process that decides whether it ships.