데이터·AI 스킬

Prepare an evaluation framework before fine-tuning a language model. Build labeled examples, checks for each failure type, and a base-model benchmark, while calibrating model-based judges against human labels to support comparisons after training.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build an evaluation set from agent traces
• Create separate checks for each failure type
• Calibrate an LLM judge against human labels

Turn graded execution traces and production logs into model training examples and preferred-versus-rejected response pairs. Select useful records, remove sensitive information, exclude evaluation examples, and preserve links to the original runs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Convert high-scoring successful runs into training examples
• Use expert-corrected failures as training examples
• Pair passing and failing responses to the same task

Prepare and review LoRA or QLoRA settings for adapting language models using example responses. Choose trainable layers, adapter capacity, learning rate, and memory-related options, then produce configuration values for a downstream training script.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing a LoRA configuration for supervised fine-tuning
• Reviewing rank, alpha, and learning rate settings
• Choosing LoRA or QLoRA based on GPU memory

Design machine learning workflows from data preparation through training, validation, deployment, and monitoring. Use templates and guidance to connect stages, track versions and experiments, handle failures, and plan gradual releases with rollback options.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing an end-to-end machine learning pipeline
• Building reproducible training workflows
• Comparing models before production deployment

Design recommendation and ranking systems that select the best items for a user or situation. Organize retrieval, enrichment, filtering, scoring, selection, and background actions into six stages, then generate a runnable scaffold for your chosen stack.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing a personalized content feed
• Reranking retrieved passages for RAG
• Prioritizing suggested tasks

Prepare datasets for language model training by formatting examples, checking conversation templates, and packing examples into training sequences. Document data sources, synthetic data ratios, and validation results in a dataset card before starting a run.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Convert raw examples into training-ready JSONL
• Check conversation templates and assistant-only training targets
• Review example boundaries after sequence packing

Design backtests that evaluate trading strategies against historical data. Account for trading costs, avoid using future information or excluding delisted securities, and compare strategies using separate development and evaluation periods.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build a backtesting system for trading strategies
• Check for bias in historical performance estimates
• Compare strategies after accounting for trading costs

Calculate portfolio risk and performance measures, including potential losses, declines from past peaks, and returns relative to risk. Use multiple indicators to support risk limits, position sizing, and ongoing monitoring.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Measuring portfolio loss risk
• Comparing returns relative to risk
• Setting risk limits and position sizes

Configure supervised fine-tuning for models that process images and text. Define which components remain unchanged, set LoRA adapters for updating selected model weights, choose image resolution limits, and investigate training runs whose evaluation results fail to improve.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Configure training for an image-and-text task
• Decide whether to train vision layers
• Investigate training with flat evaluation scores

Set up machine learning training and inference on NVIDIA DGX Spark. Get guidance on choosing containers and packages, resolving CUDA compatibility errors, and checking that PyTorch can access the GPU before starting a workload.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Setting up a new DGX Spark for training or inference
• Diagnosing CUDA compatibility and import errors
• Choosing between containers and direct pip installation

Plan memory use and monitor long training jobs on NVIDIA DGX Spark. It guides troubleshooting for out-of-memory failures, tracks temperature and power alongside training logs, and helps assess competition between training and inference workloads.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Estimating available memory before training
• Troubleshooting out-of-memory failures
• Investigating slowdowns during long training jobs

Evaluate LLM applications using automated scores, human reviews, and model-based judging. Build repeatable checks to compare models or prompts, assess answer quality, and detect declines in performance before deployment.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Comparing models and prompts
• Checking quality after prompt changes
• Detecting performance declines before deployment

Design AI applications with LangChain 1.x and LangGraph, libraries for coordinating language models and workflows. Build agents that use external tools, manage conversation history and saved state, process documents, and support tracing and testing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build an AI agent that calls external tools
• Manage conversation history and saved execution state
• Create document processing and retrieval workflows

Combine vector search, which finds similar meanings, with keyword search for exact terms. Design retrieval for search engines and RAG systems that supply reference material to AI, using methods to merge and rerank results.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Improving retrieval for RAG systems
• Finding names and codes through exact matching
• Supporting searches with specialized vocabulary

Choose embedding models, which represent text as numerical vectors, for meaning-based search and RAG applications. Compare options for code, prose, and multilingual content, and plan document splitting, preprocessing, caching, and dimension reduction to improve retrieval quality.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing an embedding model for RAG
• Reviewing document chunk size and boundaries
• Planning code or specialist document search

Design and refine prompts for AI applications using examples, reusable templates, and structured outputs such as JSON. Test variations for accuracy, consistency, response time, and token usage to diagnose unreliable answers and formatting failures.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Refine prompts that produce inconsistent answers
• Build reusable prompt templates with variables
• Design JSON outputs that follow a defined schema

Build AI applications that answer questions using retrieved documents. Covers vector databases, text embeddings that represent meaning as numbers, search strategies, and result reranking to connect language models with external knowledge.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building Q&A systems for internal documents
• Adding domain knowledge to chatbots
• Implementing natural language document search

Check ten recurring problems before or during machine learning runs on NVIDIA DGX Spark. Diagnose startup failures, out-of-memory errors, and falling throughput, with guidance on compatible environments, resource use, numeric formats, and training across two devices.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking a DGX Spark before a long training run
• Diagnosing memory errors despite apparent free capacity
• Investigating throughput drops during training

Improve slow Apache Spark jobs by reviewing data partitions, caching, memory settings, and shuffles, which move data between workers. Use the guidance to investigate bottlenecks and tune pipelines for larger datasets.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating slow Spark jobs
• Tuning memory and executor settings
• Reducing data skew and shuffle traffic

Build Apache Airflow workflows for data pipelines and scheduled jobs. The skill guides task dependencies, retries, waiting for conditions, testing, and deployment, with patterns for tasks that can be safely rerun.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building scheduled data pipelines
• Designing task order and dependencies
• Implementing custom tasks and condition checks

Design dbt data transformations with clearly organized models, data quality tests, documentation, and incremental processing that updates only part of a dataset. Use it to structure analytics tables and organize a dbt project.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Organizing a dbt project into model layers
• Adding data quality tests
• Designing incremental updates for large tables

Turn analysis into reports and presentations that explain what the numbers mean. Combine charts, context, and a clear narrative to highlight key findings, connect them to audience goals, and propose next steps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Present analytical findings to executives
• Prepare quarterly business reviews
• Structure data-based investor presentations

Build data quality checks with Great Expectations, dbt tests, and data contracts, which define shared expectations between teams. Check missing values, duplicates, and freshness, then integrate validation into data pipelines and CI/CD.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check data for missing values and duplicates
• Build a dbt test suite
• Define shared data contracts between teams

Turn supplied data into a suitable chart, dashboard, or visual explanation. The workflow chooses readable ways to show comparisons, includes source and assumption notes, and checks axes, units, and missing values without inventing data or hiding uncertainty.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing a chart for a specific comparison
• Creating a dashboard from data
• Adding sources and assumptions to a visual explanation