ML

Author

Marcus Lee

Lead AI Infrastructure Engineer

Built and scaled AI systems that handle millions of requests. I write about what separates tutorial AI from production AI — the hard lessons, the battle-tested patterns.

DevOps & DeployAI AgentsAPIs & Backends

13 Articles by Marcus Lee

Optimizing AI Agent Policies with Reinforcement Learning
AI Agents

Optimizing AI Agent Policies with Reinforcement Learning

Reinforcement learning optimizes AI agent policies in complex environments, skip the theory and focus on production-grade solutions

July 12, 202625 min
Securing LLM APIs with OAuth and JWT
LLMs & Models

Securing LLM APIs with OAuth and JWT

Secure your LLM APIs with OAuth and JWT authentication using FastAPI and MongoDB, a production-ready solution

July 12, 202625 min
Deploying Question Answering Models with Hugging Face Transformers
LLMs & Models

Deploying Question Answering Models with Hugging Face Transformers

Learn to deploy a question answering model using Hugging Face Transformers and AWS SageMaker for production-ready AI

July 12, 202625 min
Explainable AI with SHAP and LIME Libraries
AI Tooling

Explainable AI with SHAP and LIME Libraries

Implement explainable AI with SHAP and LIME libraries for transparent model predictions

July 11, 202625 min
Building Distributed AI Training Clusters
AI Tooling

Building Distributed AI Training Clusters

Distributed AI training with Slurm and NVIDIA GPUs for production-grade performance

July 11, 202625 min
Custom AI Dataset Creation with Active Learning
AI Tooling

Custom AI Dataset Creation with Active Learning

Learn how to create a custom AI dataset using active learning and weak supervision, essential for production-grade AI models

July 11, 202625 min
Monitoring AI Model Drift with Prometheus and Grafana
LLMs & Models

Monitoring AI Model Drift with Prometheus and Grafana

Monitor AI model drift with Prometheus and Grafana for production-grade reliability. Learn how to track changes in your AI model's performance over time.

July 11, 202625 min
Automating AI Data Preprocessing with Apache Beam
AI Tooling

Automating AI Data Preprocessing with Apache Beam

Automate AI data preprocessing with Apache Beam and Google Cloud Dataflow for efficient pipelines, including data ingestion and model training

July 11, 202620 min
Azure Machine Learning Hyperparameter Tuning
AI Tooling

Azure Machine Learning Hyperparameter Tuning

Automated hyperparameter tuning with Azure Machine Learning, boosting model performance

July 10, 202620 min
Reinforcement Learning with PyTorch: A Production Guide
AI Tooling

Reinforcement Learning with PyTorch: A Production Guide

Implement reinforcement learning with PyTorch for production-grade AI. Learn from a battle-tested engineer.

July 10, 202625 min
Cache Smarter: Using Redis in Node.js
APIs & Backends

Cache Smarter: Using Redis in Node.js

Boost app performance with Redis caching in Node.js. Skip the theory, here's what works

July 10, 202620 min
Building Production RAG Pipelines with Supabase pgvector
RAG & Search

Building Production RAG Pipelines with Supabase pgvector

Learn how to build a production-grade RAG pipeline using Supabase pgvector for efficient search and retrieval of data

July 9, 202625 min
JavaScript Promises and Async Await Explained
AI Tooling

JavaScript Promises and Async Await Explained

Learn JavaScript Promises and Async Await with production examples. Master async programming for efficient code

July 8, 202625 min