Applied AI is a curated knowledge repository of artificial intelligence & machine learning use cases, best practices, lessons learned, tools, and techniques, adopted by leading technology or tech-savvy organizations.
Numerous organizations frequently share their insights and expertise, encompassing best practices, tools, and techniques that shape their engineering culture. They do this through various public platforms such as engineering blogs, conferences, and meetups. This repository compiles and presents content gathered from these sources.
- Artificial Intelligence
- Machine Learning
- Deep Learning
- Generative AI
- Large Language Models
- Prompt Engineering
- Retrieval-Augmented Generation (RAG)
- MLOps
- Data Engineering
- Responsible AI
Airbnb
- Airbnb’s AI-powered photo tour using Vision Transformer
- Automation Platform v2: Improving Conversational AI at Airbnb
- Transforming Location Retrieval at Airbnb: A Journey from Heuristics to Reinforcement Learning
- Chronon, Airbnb’s ML Feature Platform, Is Now Open Source
- Airbnb Brandometer: Powering Brand Perception Measurement on Social Media Data with AI
- Prioritizing Home Attributes Based on Guest Interest
- Learning To Rank Diversely
- Building Airbnb Categories with ML & Human in the Loop
- Wisdom of Unstructured Data: Building Airbnb’s Listing Knowledge from Big Text Data
Algolia
Asos
Autotrader
BlaBlaCar
- How we used machine learning to fight fraud at BlaBlaCar — Part 1
- How we built our machine learning pipeline to fight fraud at BlaBlaCar — Part 2
- How BlaBlaCar leverages machine learning to match passengers and drivers - Part 2
- How BlaBlaCar leverages machine learning to match passengers and drivers - Part 1
Brian Impact Foundation
Canva
Dropbox
- Bye Bye Bye...: Evolution of repeated token attacks on ChatGPT models
- Bringing AI-powered answers and summaries to file previews on the web
- From AI to sustainability, why our latest data centers use 400G networking
eBay
- Background Enhancement Tool Turns Any Photo Into a Studio-Quality Product Image
- eBay's Responsible AI Principles
- Cutting Through the Noise: Three Things We've Learned About Generative AI and Developer Productivity
- Podcast: Nitzan Mekel-Bobrov on AI, the Future of Shopping Online, and the Value of Building In-House
- New Social Caption Generator Uses AI to Help Sellers Post More Easily
- eBay Exec on How Artificial Intelligence Will Bring a ‘Paradigm Shift’ to Ecommerce
- ‘Magical’ Listing Tool Harnesses the Power of AI to Make Selling on eBay Faster, Easier, and More Accurate
- Evolving Recommendations: A Personalized User-Based Ranking Model
- Beyond Words: How Multimodal Embeddings Elevate eBay's Product Recommendations
- eBay Execs Talk Generative AI and Computer Vision at VentureBeat Transform Conference
- eBay’s Blazingly Fast Billion-Scale Vector Similarity Engine
- How eBay Created a Language Model With Three Billion Item Titles
Estee Lauder
Etsy
Expedia
- Learning Embeddings for Lodging Travel Concepts
- Traveling Just Got a Lot Smarter with Romie
- Choosing the Right Candidates for Lodging Ranking
- Using Synthetic Search Data for Flights Price Forecasting
- Expedia Group’s Customer Lifetime Value Prediction Model
- Generating Diverse Travel Recommendations
- Increasing Travelers’ Engagement Through Price Alerts
- Candidate Generation Using a Two Tower Approach With Expedia Group Traveler Data
GitHub
- Unlocking the power of unstructured data with RAG
- What is retrieval-augmented generation, and what does it do for generative AI?
- Hard and soft skills for developers coding in the age of AI
- How AI code generation works
- Fixing security vulnerabilities with AI
- A developer’s second brain: Reducing complexity through partnership with AI
- How we’re experimenting with LLMs to evolve GitHub Copilot
- The architecture of today’s LLM applications
- Demystifying LLMs: How they can do things they weren’t trained to do
- How to build an enterprise LLM application: Lessons from GitHub Copilot
- A developer’s guide to prompt engineering and LLMs
- Inside GitHub: Working with the LLMs behind GitHub Copilot
- How companies are boosting productivity with generative AI
- How generative AI is changing the way developers work
- Generative AI-enabled compliance for software development
- What developers need to know about generative AI
GitLab
GoDaddy
Grab
- LLM-assisted vector similarity search
- Leveraging RAG-powered LLMs for Analytical Tasks
- Evolution of Catwalk: Model serving platform at Grab
- Enabling conversational data discovery with LLMs at Grab
- Unveiling the process: The creation of our powerful campaign builder
- LLM-powered data classification for data entities at scale
Instacart
- Enhancing FoodStorm with AI Image Generation
- Distinguished Speaker Series with Ping Li: ML-Enhanced Sparse Vector Search with Privacy Protection
- Unveiling the Core of Instacart’s Griffin 2.0: A Deep Dive Into the Model Serving Platform
- Unlocking Efficiency: How Ava Became Our AI Productivity Partner
- One model to serve them all
- Monte Carlo, Puppetry and Laughter: The Unexpected Joys of Prompt Engineering
- Unveiling the Core of Instacart’s Griffin 2.0: A Deep Dive into the Machine Learning Training Platform
- Introducing Griffin 2.0: Instacart’s Next-Gen ML Platform
- Scaling Productivity with Ava — Instacart’s Internal AI Assistant
- Supercharging ML/AI Foundations at Instacart
- Adopting dbt as the Data Transformation Tool at Instacart
- The Next Era of Data at Instacart
- How Instacart Modernized the Prediction of Real Time Availability for Hundreds of Millions of Items While Saving Costs
Mercado Libre
Mercari
- Fine-Tuning an LLM to Extract Dynamically Specified Attributes
- LMM based Approach to Large-scale Item Category Classification
- LM-based query categorization for query understanding
- Leveraging LLMs in Production: Looking Back, Going Forward
- The Bitter Lesson about Engineers in a ChatGPT World
- Putting the Voice of Customers into the Software Development Process
- Mercari’s Journey Integrating AI & Search at Berlin Buzzwords 2023
- Improving Item Recommendation Accuracy Using Collaborative Filtering and Vector Search Engine
- Model management for client side ML powered by Firebase
- The Journey to Machine-Learned Re-ranking
- Do We Need Engineers in a ChatGPT World?
Meta
- Various AI/ML research papers submitted by Meta are available here
- Meta AI blog
- Leveraging AI for efficient incident response
- Maintaining large-scale AI capacity at Meta
- Our next-generation Meta Training and Inference Accelerator
- PVF: A novel metric for understanding AI systems’ vulnerability against SDCs in model parameters
- Optimizing RTC bandwidth estimation with machine learning
- Logarithm: A logging engine for AI training workflows and services
- Building Meta’s GenAI Infrastructure
- Improving machine learning iteration speed with faster application build and packaging
- Lazy is the new fast: How Lazy Imports and Cinder accelerate machine learning at Meta
- How Meta is advancing GenAI
- Serverless Jupyter Notebooks at Meta
- Building custom silicon for the future of AI
- Introducing Code Llama, a state-of-the-art large language model for coding
- Watch: Meta’s engineers on building network infrastructure for AI
- How Meta is creating custom silicon for AI
- AI debugging at Meta with HawkEye
- Arcadia: An end-to-end AI system performance simulator
- MTIA v1: Meta’s first-generation AI inference accelerator
Morgan Stanley
Notion
Nubank
Slack
Slalom Build
Sourcegraph
Uber
- Open Source and In-House: How Uber Optimizes LLM Training
- Genie: Uber’s Gen AI On-Call Copilot
- QueryGPT – Natural Language to SQL Using Generative AI
- Personalized Marketing at Scale: Uber’s Out-of-App Recommendation System
- DataK9: Auto-categorizing an exabyte of data at field level through AI/ML
- From Predictive to Generative – How Michelangelo Accelerates Uber’s AI Journey
- DragonCrawl: Generative AI for High-Quality Mobile Testing
- Scaling AI/ML Infrastructure at Uber
- Stopping Uber Fraudsters Through Risk Challenges
- Model Excellence Scores: A Framework for Enhancing the Quality of Machine Learning Systems at Scale
- The Transformative Power of Generative AI in Software Development: Lessons from Uber’s Tech-Wide Hackathon
- Innovative Recommendation Applications Using Two Tower Embeddings at Uber
- Demand and ETR Forecasting at Airports
- Risk Entity Watch – Using Anomaly Detection to Fight Fraud
- Accelerating Advertising Optimization: Unleashing the Power of Ads Simulation
- uVitals – An Anomaly Detection & Alerting System
- Project RADAR: Intelligent Early Fraud Detection System with Humans in the Loop
- DeepETA: How Uber Predicts Arrival Times Using Deep Learning
- Uber’s Real-Time Document Check
- How Uber Optimizes the Timing of Push Notifications using ML and Linear Programming
- ML Education at Uber: Program Design and Outcomes
- ML Education at Uber: Frameworks Inspired by Engineering Principles
Walmart
- Managing Secure API Access to LLMs in Distributed Systems with Dataflow
- Creating Web App For File Interactions Using RAG: A Developers Guide
- Exploring the World of Vector Databases: A Comprehensive Guide
- Using Predictive and Gen AI to Improve Product Categorization at Walmart
- AI-Driven Continuous Monitoring: The Future of Third-Party Risk Management
- Build your own GPT (BYO-GPT)
- Textual Titans: A Large Language Model Odyssey
- Evaluation of RAG Metrics using RAGA
- Deploying RAGs in production — Part 2
- Deploying RAGs in production — Part 1
- Extracting Product Attributes from PDFs using PAE Framework
- Augmentation Techniques for Imbalanced text Classification
- Transforming Text Classification with Semantic Search Techniques — Faiss
Wix
- Wix streamlines website content creation with GPT.
- Real-World Forecasting with Deep Learning: How We Do It at Wix
- Customizing LLMs for Enterprise Data Using Domain Adaptation: The Wix Journey
- AI for Revolutionizing Customer Care Routing System at Wix
- SageMaker Batch Transform Unleashed: My Journey at Wix to Achieve Scalable ML
- Beyond Content Generation: AI-Based Layout Generation for Graphic Design
Following resources from AI vendors like OpenAI, Anthropic, and Databricks provide valuable insights into how businesses are leveraging AI to solve complex challenges and drive innovation.
Contributions welcome! Read the contribution guidelines first.
To the extent possible under law, Unmesh Gundecha has waived all copyright and related or neighboring rights to this work.
If you decide to use this anywhere, please credit @upgundecha on X. Also, if you like my work, check out my other projects on GitHub.