AI-Engineering
Research into AI engineering interview assignments, take-home challenges, and hiring practices from Q4 2025 / Q1 2026
File Explorer
- 1. What Is a Large Language Model (Conceptual Layer).md
- 2. Transformer Architecture (System Layer).md
- 3. Tokenization & Embeddings (Representation Layer).md
- 4. Training Paradigm (Learning Layer).md
- 5. Inference Mechanics (Runtime Layer).md
- 6. Model Ecosystem & Types.md
- 7. Evaluation & Benchmarks.md
- 8. Limitations & Failure Modes.md
- 1. Mental Model of Prompting (Foundation Layer).md
- 2. Prompt Structure & Anatomy.md
- 3. Instruction Design Patterns.md
- 4. Structured Output Prompting.md
- 5. Prompt Robustness & Reliability.md
- 6. Prompt Evaluation & Metrics.md
- 7. Security & Safety in Prompting.md
- 1. Introduction to Context Engineering.md
- 2. What Constitutes Context.md
- 3. Techniques to Manage Context.md
- README.md
- 1. Introduction to Orchestration.md
- 2. Core Orchestration Patterns.md
- 3. Structured Output.md
- 4. Tool Integration & Function Calling.md
- 1. Introduction to Vector Databases.md
- 2. Embeddings & Vector Space Fundamentals.md
- 3. Ecosystem & Tools.md
- README.md
- 1. Introduction to Memory in AI Systems.md
- 2. Types of Memory.md
- 3. Memory Storage Mechanisms.md
- 4. Memory Retrieval Strategies.md
- 5. Memory Compression & Pruning.md
- 6. Memory in Agentic Systems.md
- 7. Memory Failure Modes.md
- 8. Tools & Frameworks for Memory Management.md
- 1. Fine-Tuning Fundamentals.md
- 10. Evaluation of Fine-Tuned Models.md
- 11. Overfitting & Catastrophic Forgetting.md
- 12. Adapter Management & Versioning.md
- 13. Deployment of Fine-Tuned Models.md
- 2. Pretraining vs Fine-Tuning.md
- 3. Supervised Fine-Tuning (SFT).md
- 4. Preference-Based Tuning (RLHF, DPO – Overview).md
- 5. Parameter-Efficient Fine-Tuning (PEFT).md
- 6. LoRA (Low-Rank Adaptation).md
- 7. QLoRA (Quantized LoRA).md
- 8. Data Preparation for Fine-Tuning.md
- 9. Fine-Tuning vs RAG vs Prompt Engineering.md
- 1. Introduction to AI Automation.md
- 2. Automation Design Patterns.md
- 3. Tool Integration for Automation.md
- 4. Workflow Orchestration Tools.md
- README.md
- 1. Foundations of Agentic Planning.md
- 10. Evaluation of Reasoning Systems.md
- 2. Reasoning Patterns in LLM Systems.md
- 3. Single-Agent Planning.md
- 4. Task Decomposition Strategies.md
- 5. Iterative Reasoning Loops.md
- 6. Tool-Aware Reasoning.md
- 7. State-Aware Planning.md
- 8. Planning Constraints & Control.md
- 9. Failure Modes in Planning Systems.md
- 1. Introduction to Model Context Protocol (MCP).md
- 2. Tool Interface Standardization.md
- 3. Client–Server Architecture for Agents.md
- 4. Capability Discovery.md
- Frameworks & Libraries.md
- README.md
- 1. AI Interaction Design.md
- 2. Trust & Transparency.md
- 3. Latency & Responsiveness.md
- 4. Feedback & Control.md
- CD for AI Systems.md
- 1. Deployment Architectures.md
- 2. Backend Deployment.md
- 3. Containerization & Infrastructure.md
- 4. Model Serving (Self-Hosted).md
- 5. Scaling & Performance.md
- 1. Request & Trace Logging.md
- 2. Token, Cost & Latency Monitoring.md
- 3. Workflow-Level Monitoring.md
- 4. Quality & Behavior Monitoring.md
- 5. Alerting & Incident Response.md
- 1. Input Safety.md
- 2. Output Filtering.md
- 3. Tool Safety.md
- 4. Prompt Injection & Jailbreak Defense.md
- 5. Policy & Usage Controls.md
- 6. Human-in-the-Loop Safeguards.md
- 1. Data Governance.md
- 2. Access & Identity Management.md
- 3. Model & Prompt Governance.md
- 4. Compliance & Regulatory Considerations.md
- 5. Risk Management & Documentation.md
- 6. Auditability & Transparency.md
- 1. What Managed AI Platforms Provide.md
- 2. Core Capabilities.md
- 3. Deployment & Scaling Features.md
- 4. Security & Compliance.md
- 5. Popular Managed AI Platforms.md
- 6. When to Use Managed Platforms.md
- 7. Trade-Offs.md
- README.md
- 01-theory.md
- 02-coding.md
- 03-project-deep-dive.md
- 04-ai-system-design.md
- 05-behavioral.md
- 06-home-assignments.md
- questions.md
- 01-interview-process.md
- 02-questions.md
- 03-get-hired.md
- 04-after-the-interview.md
- 05-trends.md
- README.md
- from-backend-engineer.md
- from-data-engineer.md
- from-data-scientist.md
- from-frontend-engineer.md
- from-ml-engineer.md
- README.md
- README.md
- README.md
- 01-my-vision.md
- 02-skills.md
- 03-responsibilities.md
- 04-use-cases.md
- 05-reality-vs-postings.md
- README.md
- 01-a-day-of-ai-engineer.md
- 02-defining-the-role.md
- 03-the-interview-process.md
- 04-take-home-assignments.md
- README.md
- awesome.md
- LICENSE
- README.md
# Use via CDN
jsDelivrjsDelivr serves any public GitHub repository as a CDN with zero setup. Pick a version and a file to get a ready-to-paste link and snippet.
Link
Example
// repository documentation
Was this content helpful?
(0 ratings)