Practical, hands-on notes on building production AI systems: agentic AI, RAG, LLM fine-tuning, RLHF, MLOps, and real-time inference. Written from real engineering work, not marketing.
Author: Rehan Malik
- Agentic AI and multi-agent systems
- Retrieval-augmented generation (RAG)
- LLM fine-tuning (LoRA, QLoRA, RLHF, DPO)
- MLOps and model monitoring
- Real-time inference and serving
- Production RAG Pipelines with Re-ranking — 2026-07-30
- Production RAG Pipelines with Re-ranking — 2026-07-29
- High-Performance Local LLM Inference & Agentic Workflows — 2026-07-28
- Hybrid RAG Architectures for Production Workloads — 2026-07-27
- Graph RAG and Knowledge Graphs for LLMs — 2026-07-26
- Multi-Agent AI Orchestration Patterns — 2026-07-25
- Agentic Coding Assistants Architecture — 2026-07-25
- clear topic name — 2026-07-24
- Unified Fine-Tuning Across LLMs and Vision-Language Models (VLMs) — 2026-07-23
- SuperAgents for Long-Horizon Multi-Tasking — 2026-07-23
- — 2026-07-21
- Real-Time AI Inference Optimization — 2026-07-20
- "Context Scaling in Robotic Policies with Dynamic Novel View Synthesis" — 2026-07-19
- Model Context Protocol and Tool Use — 2026-07-18
- Multi-Agent AI Orchestration Patterns — 2026-07-18
- Graph RAG and Knowledge Graphs for LLMs — 2026-07-16
- Model Context Protocol and Tool Use — 2026-07-15
- Agentic Coding Assistants Architecture — 2026-07-15
- LLM Fine-Tuning at Scale with LoRA — 2026-07-14
- Production RAG Pipelines with Re-ranking — 2026-07-14
Open to AI/ML roles and collaborations. LinkedIn