READ. UNDERSTAND. PRACTICE.
Prepare for your next interview.
Explore algorithm tutorials, coding and system design questions, interview experiences, and computer science study guides.
20,926 resources · Page 52 of 872
Articles
LLMs 39. Reinforcement Learning Applications in Natural Language Processing
This technical interview prep framework covers reinforcement learning applications in natural language processing, including policy optimization…
Articles
LLMs 40. Large Language Models (LLMs) — Training Section
This learning-oriented guide covers LLM training data, formats, selection, and scaling across supervised fine-tuning (SFT), reward modeling (RM)…
Articles
LLMs 41. Large Language Models (LLMs) — Methods for Generating SFT Data
This guide explains practical methods for constructing supervised fine-tuning (SFT) datasets for large language models, covering human annotation…
Articles
LLMs 42. LLMs: Hardware, Memory, and Performance
This practical guide examines LLM hardware, memory, and performance trade-offs, covering parameterization versus system constraints, memory…
Articles
LLMs 43. GPU Memory Optimization Strategies
This guide covers GPU memory optimization strategies for modern deep learning and large language models, focusing on memory bottlenecks, gradient…
Articles
LLMs 44. Distributed Training of Large Language Models (LLMs)
Distributed training of large language models for interviews: data, tensor, and pipeline parallelism, sharding, and trade-offs.
Articles
LLMs 45. Illustrated Guide to Distributed Training (I): Pipeline Parallelism
This illustrated guide to distributed training explains pipeline parallelism, including why it matters, the specific problems it solves (such…
Articles
LLMs Document-Based Dialogue Using LLM + Vector Database (14)
This practical learning guide covers design and implementation of document-based dialogue systems using large language models and vector databases…
Articles
LLMs Document Q&A — PDF Parsing Key Issues (16)
The resource covers PDF parsing challenges for LLM-based document Q&A systems, including layout and structure extraction, OCR and image-text handling…
Articles
LLMs 19. Large-Model External Knowledge Base Optimization — How to Use Large Models to Assist Retrieval?
The resource covers optimization of external knowledge retrieval for large language models, including retrieval-augmented generation pitfalls, query…
Articles
LLMs Large-Model RAG Explained (15)
This systems-level guide explains retrieval-augmented generation (RAG), covering architecture and components such as retrieval and indexing, vector…
Articles
LLMs Large Models (LLMs) RAG Edition Analysis — Table Recognition Methods (17)
This analysis examines table recognition methods for large language models and RAG systems, covering model architectures, OCR and layout parsing…
Articles
LLMs Large Models (LLMs) RAG Edition Analysis — Text Chunking (18)
This guide covers text chunking strategies for Retrieval-Augmented Generation (RAG) systems, explaining why chunking matters, how different chunking…
Articles
LLMs Practical Lancchain RAG Question (13)
This guide covers building retrieval-augmented generation (RAG) systems with LangChain, including retrieval and vector embeddings, document stores…
Articles
Load Balancing vs Consistent Hashing: The 80% Cache Mistake
Load balancers spread traffic; consistent hashing owns state. A production war story on cache remap storms, hash rings, virtual nodes, and hot-key salting.
Articles
LoadRunner Interview Questions: Correlation, Replay Failures, and Workload Pacing
Practice LoadRunner interview questions on correlation, failed replay, business assertions, pacing, think time and credible workload calculations.
Articles
Locust Interview Questions: User Models, Wait Times, and Distributed Load
Practice Locust interview questions on user models, wait times, distributed workers, and generator limits, with workload calculations and a tested example.
Articles
Log Parsing Interview Practice: Streaming Aggregation and Bounded Memory
Practice log parsing interviews with a tested streaming exercise. Define malformed rows, time boundaries, ties, duplicate IDs, and the limits of bounded memory.
Articles
Logging Framework Low-Level Design Interview: Sinks, Backpressure, and Shutdown
Prepare a logging framework design interview with bounded sink queues, explicit backpressure, flush barriers, and shutdown results that expose unresolved work.
Articles
Logistic Regression Interview Questions: Log-Odds, Separation, and Misleading Interpretations
Practice logistic regression interview questions on log-odds, separation, regularization, and coefficient traps with worked examples and clear explanations.
Articles
Long-Context Evaluation Interview Questions: Position Bias and Evidence Retrieval
Prepare for long-context evaluation interviews: control evidence position, diagnose retrieval failures, score citations and abstention, and use fair budgets.
Articles
Looker LookML Interview Questions: Joins, Fanout, Explores, and Measures
Prepare for Looker LookML interviews with practical join, fanout, Explore, primary-key, and measure examples plus a debugging checklist.
Articles
Looker Studio Interview Questions: Data Blends, Aggregation, and Misleading Totals
Looker Studio interview questions: trace blend aggregation and joins, reconcile repeated costs, and diagnose filters, ratios, and misleading totals.
Articles
LLD Interview: What Low-Level Design Is and How to Crack It
LLD means low-level design: class-level design of a component — entities, relationships, APIs, patterns. How it differs from HLD and how to crack it.