Concepts in AI & ML, page 23
Document Chunking: Slicing Text for LLMs
Think of chunking as preparing text "bites" for an LLM. It breaks large documents into smaller, meaningful segments to fit a model's context window and improve search. It's essential for Retrieval-Augmented Generation (RAG) and semantic search.
Data Drift: Why Good Models Go Bad
Data drift is when a model's accuracy decays because the real-world data it was trained on has changed. This happens in fraud detection as scams evolve or in e-commerce as trends shift.
Scene Graph Generation: From Pixels to Relationships
Scene Graph Generation (SGG) moves beyond just finding objects in an image; it maps out the relationships between them. This enables deeper scene understanding for tasks like advanced image search.
Data Storage Tiering: Pay Only for the Access You Need
Treat data like items in a house: hot, frequently used data on the counter; cool, less-used data in the pantry. Cloud providers use this to price storage, letting you move old logs to cheaper tiers.
Evaluating RAG Systems: Metrics for Retrieval and Generation
Evaluating a RAG system means grading its two parts: retrieval and generation. Metrics like relevance check if the right documents were found, while faithfulness and accuracy check if the final answer correctly uses those documents.
Visual Servoing: Using Eyes to Guide a Robot's Hands
Visual servoing is like how you reach for a cup: your eyes guide your hand. A robot uses a camera to continuously correct its motion toward a target, closing the loop between seeing and doing. It's key for robotic arms, drones, and surgical bots.
Reserved Instances vs. Savings Plans: Pre-pay for Cloud Discounts
Think of Reserved Instances and Savings Plans as buying cloud compute in bulk for a discount. You commit to a certain usage level for 1-3 years to save money on steady-state workloads like production databases.
Cross-Encoder Re-ranking: Accuracy Over Speed
A cross-encoder re-ranks search results by reading the query and each document together, allowing it to spot subtle connections. It's the second, high-precision step in a search pipeline, re-ordering a small list of candidates.
IaC for MLOps: Your ML Factory's Blueprint
Treat ML infrastructure—training clusters, model registries, serving endpoints—as code in version-controlled files. This ensures reproducible experiments and consistent deployments across environments.
Affordance Learning: Teaching AI What Objects Do
Instead of just naming objects, affordance learning teaches AI to see potential actions—a chair is for sitting, a knob is for turning. This is crucial for robotics, where a machine must know how to interact with novel items.
Cloud Cost Anomaly Detection: Finding Waste
Think of it as a smoke detector for your cloud bill, distinguishing 'good' growth-related costs from 'bad' waste. It automatically flags unexpected spending spikes from misconfigurations or bugs.
Agentic Reasoning: LLMs that Plan, Act, and Learn
Agentic reasoning treats an LLM as an autonomous agent that interacts with its environment. It plans tasks, uses tools like APIs, and learns from feedback to solve complex problems. The footgun is assuming its plans are optimal or actions are always correct.
Visual Commonsense Reasoning (VCR): From Recognition to Cognition
VCR pushes AI from simple object recognition to human-like reasoning by asking not just 'what' is in an image, but 'why.' Models must select both the correct answer and the correct rationale, exposing models that guess answers based on shallow correlations.
Slash Your Cloud Bill by Taming Data Egress Costs
Data egress is the tax for moving data out of a cloud provider's network, a common cost in MLOps when moving models or datasets. To save money, keep compute and data in the same region. The footgun is forgetting that traffic between regions also counts.
Agent Memory: Short-Term vs. Long-Term Recall
Agent memory gives an LLM a sense of history, separating fleeting conversation context from persistent knowledge. Short-term memory tracks the current chat, while long-term memory recalls user facts across sessions.
Algorithmic Bias: When Code Creates Unfair Outcomes
Algorithmic bias is a mirror reflecting flawed human data, leading to systematically unfair outcomes. It appears in hiring tools favoring one gender or loan systems denying certain groups. The footgun is assuming tech is neutral; the bias is in the data.
Pretext Tasks: Making Data Teach Itself
A pretext task is a fake problem you invent for a model so it learns from unlabeled data. For example, asking it to predict a missing image patch forces it to learn about objects. This is the core of self-supervised learning.
Idempotent Data Pipelines: Reruns Without Side Effects
An idempotent pipeline gives the same output for the same input, no matter how many times you run it. This lets you safely retry failed jobs without side effects, which is crucial for scheduled batch inference or feature engineering tasks.
LangChain Agents: Giving LLMs a Toolkit
A LangChain Agent is an LLM given a toolkit and a goal. The agent's 'harness' prompts the model to pick tools, call them in a loop, and reason about the results until the task is complete. Use it to query databases or call external APIs.
Disparate Impact: When Fair Rules Aren't Fair
Disparate impact is when a neutral rule causes a discriminatory outcome, regardless of intent. This is key in ML fairness, where an algorithm might deny loans to one group more than another, even with objective rules.
We are hiring for this. Every open role lists the topics its interview covers, so you can prepare for the real thing rather than guessing.
See open roles