Archive
120 posts, newest first
2026
- Parsing Documents: PDFs, Tables, Scans and Layout (opens on Medium)AI System Design
- Cleaning and Deduplication Before Anything Is Embedded (opens on Medium)AI System Design
- I Tested Jev and Laya, Two New AI Decision Models, on Games They Were Never Trained For (opens on Medium)LLM Architectures
- Decision Models: How Jev and Laya Decide Without Writing Text (opens on Medium)LLM Architectures
- Shapes, FLOPs, and Memory: Sizing a Transformer Before You Run It (opens on Medium)LLM Architectures
- The Ingestion Pipeline: What You Ingest, What You Store, and What Starts the Rest (opens on Medium)AI System Design
- A Baseline RAG and a Golden Set Before Any Optimisation (opens on Medium)AI System Design
- The RAG Pipeline as Building Blocks: Seven Ways an Answer Goes Wrong (opens on Medium)AI System Design
- A Framework for Deciding Where Retrieval Work Happens (opens on Medium)AI System Design
- Caching for LLM Systems: Exact, Semantic, and Provider Prefix Caches (opens on Medium)AI System Design
- How Netflix Runs Its Own LLM Serving Stack (opens on Medium)LLM-Era System Design Case Studies
- Uber's GenAI Gateway: One Control Point for Company-Wide LLM Access (opens on Medium)LLM-Era System Design Case Studies
- How Dropbox Dash Grounds Its Agents Against Hallucination (opens on Medium)LLM-Era System Design Case Studies
- Reliability & Fault Tolerance in LLM Systems: Fallbacks & Guardrails (opens on Medium)AI System Design
- Reliability for Model-Locked Systems: When Cross-Model Fallback Isn't an Option (opens on Medium)AI System Design
- Evaluating LLM Systems: Offline Evals, Online Evals, LLM-as-Judge (opens on Medium)AI System Design
- pgvector Internals Overview: How Postgres Learned to Speak Vector (opens on Medium)Postgres Series
- Hybrid Search: Combining Vector Similarity with Metadata Filters and Keyword Search (opens on Medium)Vector Databases
- Distributed Systems Concerns: Replication, Consistency, and Query Routing (opens on Medium)Vector Databases
- Sharding and Partitioning at Scale: Splitting Billions of Vectors Across Machines (opens on Medium)Vector Databases
- Storage Architecture: Memory, Disk, and Memory-Mapped Layouts at Billion-Vector Scale (opens on Medium)Vector Databases
- Indexing Deep Dive: DiskANN and Disk-Resident Graphs (opens on Medium)Vector Databases
- Vector Compression and Quantisation: Fitting Billions of Vectors in Memory (opens on Medium)Vector Databases
- Indexing Deep Dive: IVF and IVF-PQ (opens on Medium)Vector Databases
- Indexing Deep Dive: HNSW, Under the Hood (opens on Medium)Vector Databases
- The Curse of Dimensionality: Why Exact Nearest-Neighbor Search Does Not Scale (opens on Medium)Vector Databases
- Inside the Encoder: Tokens, Attention, and How a Transformer Actually Works (opens on Medium)Vector Databases
- Distance Metrics and Similarity Search: Cosine, Euclidean, and Dot Product (opens on Medium)Vector Databases
- Scaling Contrastive Training: Batch Size, GPU Gathering, and Gradient Caching (opens on Medium)Vector Databases
- How Embedding Models Actually Learn: The Math Behind Contrastive Training (opens on Medium)Vector Databases
- Embeddings 101: How Text, Images, and Audio Become Vectors (opens on Medium)Vector Databases
- What Is a Vector Database? Origins, Use Cases, and How It Differs from Relational and NoSQL Systems (opens on Medium)Vector Databases
- LLM Serving Architectures: Batching, KV-Cache, Multi-Tenancy (opens on Medium)AI System Design
- Orchestration & Memory: Context Management for Long-Running Agents (opens on Medium)AI System Design
- Agentic Systems: Tool Use, Planning, Multi-Step Reasoning (opens on Medium)AI System Design
- Fine-Tuning vs. RAG vs. Prompting: Choosing the Right Approach (opens on Medium)AI System Design
- Embeddings & Vector Databases: Architecture and Trade-offs (opens on Medium)Vector Databases
- Designing RAG Systems: Retrieval, Chunking, Re-ranking, Grounding (opens on Medium)AI System Design
- How AWS Lambda Runs 15 Trillion Invocations a Month: Firecracker, Snapshots, and Tiered Caches (opens on Medium)System Design Case Studies
- Pretraining vs. Post-Training: How a Text Predictor Becomes an Assistant (opens on Medium)J-Space Primer
- Chain-of-Thought and Scratchpad Reasoning: The Model Thinking Out Loud (opens on Medium)J-Space Primer
- Attention Mechanism Basics: How Tokens Reach Across the Whole Context (opens on Medium)J-Space Primer
- Procrastinate: Turning Postgres Into Your Task Queue (opens on Medium)Postgres Series
- GPT-Live: OpenAI's Full-Duplex Voice Architecture Ends the Turn-Taking Era (opens on Medium)AI Breakthroughs
- Postgres Learns to Speak Graph: Inside SQL/PGQ and PostgreSQL 19 (opens on Medium)Postgres Series
- How WhatsApp Moved 50 Billion Messages a Day With Just 32 Engineers (opens on Medium)System Design Case Studies
- Transformer Layers and the Residual Stream (opens on Medium)J-Space Primer
- Prompt Engineering as a System Design Discipline (opens on Medium)AI System Design
- A Global Workspace in Language Models: Anthropic Finds a Silent "J-Space" Inside Claude (opens on Medium)AI Breakthroughs
- Why Framing Comes Before Architecture (opens on Medium)AI System Design
- How YouTube Scaled MySQL to 2.49 Billion Users: The Vitess Story (opens on Medium)System Design Case Studies
- Why LLM-Era AI Systems Break Every Rule You Learned About ML in Production (opens on Medium)AI System Design
- PostgreSQL Internals, CDC, Kafka, and Distributed Systems Engineering Series (opens on Medium)Postgres Series
- Kafka-Based PostgreSQL → Salesforce Architecture (Part 2): How the System Actually Works (opens on Medium)Postgres Series
- PostgreSQL to Salesforce at Scale: Evolving a CDC Pipeline with Kafka (opens on Medium)Postgres Series
- Building a Reliable PostgreSQL → Salesforce CDC Pipeline: Lessons from WAL, Replication, and Failure Isolation (opens on Medium)Postgres Series
- Protecting PostgreSQL Primaries from Replication Slot Failures (opens on Medium)Postgres Series
- PostgreSQL Logical Replication at Scale: Database-Side Guardrails for 60M+ Change Events (opens on Medium)Postgres Series
- PostgreSQL Logical Replication Internals: restart_lsn vs confirmed_flush_lsn Explained (opens on Medium)Postgres Series
- Understanding PostgreSQL Logical Replication: The Complete End-to-End Flow (opens on Medium)Postgres Series
- From Hot Partitions to Stable Throughput: Lessons From Kafka in Production (opens on Medium)Backend & Infra
- How to Choose the Right Messaging System in Distributed Systems (opens on Medium)Backend & Infra
- Partitioning vs. Sharding: A Practical Guide to Scaling Beyond One Machine (opens on Medium)Backend & Infra
- How Kafka Really Works: Lessons from a 60M+ Events/Day Production Pipeline (opens on Medium)Backend & Infra
- Beyond Accuracy: A Developer's Guide to Reliable LLM Evaluation (opens on Medium)AI System Design
- How to Stop Your NL2SQL Agents From Crashing in Production: The Worker-Pool Pattern (opens on Medium)AI System Design
- Beyond Schema: Why Your AI Can't Write Good SQL (and How to Fix It) (opens on Medium)AI System Design
- Engineering Trust: A Defensive Architecture for NL2SQL Systems (opens on Medium)AI System Design
- Scaling Up RL: From Q-Tables to Deep Q-Networks (DQN) (opens on Medium)LLM Architectures
- From Q-Learning to LLMs: Mastering the Bedrock of Post-Training (opens on Medium)LLM Architectures
2025
- Scalable Inference with RDMA and Tiered KV Caching (opens on Medium)AI System Design
- The Intuition Behind LoRA & QLoRA: Fine-Tuning LLMs Without Going Broke (opens on Medium)LLM Architectures
- The 70B LLM Optimisation Playbook: From 57.5GB to 24.3GB Per GPU (opens on Medium)AI System Design
- How to Serve a 70B Model with a 128K Context on Just 8 H100s (opens on Medium)AI System Design
- Decoding Real-Time LLM Inference: A Guide to the Latency vs. Throughput Bottleneck (opens on Medium)AI System Design
- The Secret to the First Word: How LLMs Build Context with Prefill (opens on Medium)LLM Architectures
- How LLMs Understand Your Prompt: A Deep Dive into Prefill Attention (opens on Medium)LLM Architectures
- From Prompt to Response: Unpacking the Magic of LLM Inference (opens on Medium)LLM Architectures
- I Learned How Azure Functions Run My Code: A Deep Dive into the Python Worker and gRPC (opens on Medium)Azure Functions Internals
- I Learned How Azure Functions Run My Code: A Deep Dive into the Host and WebJobs SDK (opens on Medium)Azure Functions Internals
- I Spent an Entire Weekend Demystifying the Azure Functions Runtime so that You Can Learn It in 5 Minutes. (opens on Medium)Azure Functions Internals
- Messy Logging Config? Here's the dictConfig Fix (opens on Medium)Python Logging
- Python Logging Unveiled: What Happens When You Call .info()? (opens on Medium)Python Logging
- How to Choose the Right Python Logging Setup: A Breakdown of the 4 Methods (opens on Medium)Python Logging
- What Actually Happens When You Use logger.setLevel() in Python? (opens on Medium)Python Logging
- Get Your Python Logs Talking: A Clear Guide to Adapters & Filters (opens on Medium)Python Logging
- Log Like a Pro: Understanding Python's Logging Essentials (opens on Medium)Python Logging
2024
- From Data to Vectors: How Vector Databases Revolutionize Data Storage (opens on Medium)Vector Databases
- Discover the Magic Behind Your Searches: How Semantic and Vector Search Transform Your Online Experience (opens on Medium)AI System Design
- Understanding Azure Synapse Link: Initial Sync, Incremental Changes, and In-Place Updates (opens on Medium)Azure & Cloud Fundamentals
- The Mechanics of Query Expansion in RAG Systems: A Theoretical Exploration of PRF and LLM Techniques (opens on Medium)AI System Design
- Are You Combining Software Engineering and Data Engineering for Maximum Efficiency? (opens on Medium)Software Engineering
- Rediscovering Query Expansion: The Classic Technique Powering Modern AI Searches (opens on Medium)AI System Design
- Transitioning from Export to Data Lake to Azure Synapse Link: What You Need to Know? (opens on Medium)Azure & Cloud Fundamentals
- Optimizing Data Synchronization for Downstream Systems in Azure Synapse Link (opens on Medium)Azure & Cloud Fundamentals
- How Switching to Azure Synapse Link Delivers Cost Savings and Enhanced Performance (opens on Medium)Azure & Cloud Fundamentals
- Demystifying D365 F&O Data Export: A Guide to Microsoft's Data Export Solutions (opens on Medium)Azure & Cloud Fundamentals
- Managed Identities Explained (opens on Medium)Azure & Cloud Fundamentals
- Choose the proper subscription and management group strategy (opens on Medium)Azure & Cloud Fundamentals
2023
2022
2021
- Best Practices in Spring Boot Project Structure (opens on Medium)Java & Spring Boot
- Consistency in Database (opens on Medium)Backend & Infra
- Dependency Injection Explained (opens on Medium)Java & Spring Boot
- How does Spring Boot Manage Dependency? (opens on Medium)Java & Spring Boot
- Know your pom.xml (opens on Medium)Java & Spring Boot
- Do I need to scale my features? (opens on Medium)Data Science
- Multi-Module Spring Boot Project with Azure (opens on Medium)Java & Spring Boot
2020
- Microsoft Azure Structure Explained (opens on Medium)Azure & Cloud Fundamentals
- OSI Model Demystified (opens on Medium)Backend & Infra
- Is your Application Cloud-Ready (opens on Medium)Azure & Cloud Fundamentals
- Kubernetes Architecture Demystified (opens on Medium)Backend & Infra
- Singleton Pattern Made Easy (opens on Medium)Software Engineering
- Cloud Computing: Making Life easier for companies (opens on Medium)Azure & Cloud Fundamentals
- How to manage IoT devices at scale (opens on Medium)Azure & Cloud Fundamentals
- Is Abstraction a solution for most of your complex problem (opens on Medium)Software Engineering
- What's new with Azure Backup (opens on Medium)Azure & Cloud Fundamentals