SS

Blog

Technical notes, implementation write-ups, and research reflections in MDX.

2026-07-25 · 12 min read

Optimus: Autonomous EnergyPlus Building Controller

A safety-constrained physical-AI controller for autonomous building operations. Uses EnergyPlus simulation with PyEnergyPlus API, local LLM (Ollama/Qwen) or deterministic fallback for bounded planning, and hard safety validation before schedule override injection.

EnergyPlusPhysical AIBuilding ControlOllamaQwenStreamlitDocker
Read post
2026-07-15 · 12 min read

Why Distributed Training Still Bottlenecks at Scale

A practical look at gradient synchronization, communication overlap, and the hidden costs of scaling PyTorch DDP. Based on building a distributed ML training framework for heterogeneous consumer hardware.

Distributed SystemsPyTorchML Infra
Read post
2026-06-20 · 10 min read

Technical Note: Designing Reliable Multi-Agent Systems

Notes on orchestration, context management, and fault tolerance for specialized LLM agent teams. Based on building AgentForge and AI Research Orchestrator.

LLMsAgentsArchitecture
Read post
2025-11-01 · 12 min read

AgentForge: Multi-Agent Software Engineering with Local LLMs

Building a local-first multi-agent coding assistant where specialized agents (Analyst, Architect, Planner, Critic, Consensus) collaborate on software tasks—running entirely on your machine with Ollama. Focus on role specialization, structured intermediates, and local execution.

Agentic AIMulti-AgentLocal LLMsOllamaSoftware Engineering
Read post
2025-08-15 · 10 min read

Building Real-Time Speech Emotion Recognition

How I built a complete speech emotion recognition pipeline from audio preprocessing to real-time inference—published at IEEE DECoN 2025. Covers the published lightweight CNN approach and the extended project implementation with CNN-BiLSTM.

Speech AIDeep LearningTensorFlowPyTorchLibrosaReal-timeIEEE
Read post
2025-07-20 · 10 min read

AI Research Orchestrator: Multi-Agent Literature Synthesis

An autonomous research assistant that plans literature reviews, retrieves papers from academic APIs, analyzes findings, and generates structured reports—built as a modular multi-agent system in TypeScript with production and offline modes.

Multi-Agent SystemsResearch EngineeringLLMsTypeScriptSemantic ScholarOpenAlex
Read post
2025-06-20 · 12 min read

Brain MRI Tumor Segmentation: 3D U-Net to Attention + EfficientNet

An iterative research journey through volumetric brain tumor segmentation—comparing baseline 3D U-Net, EfficientNet encoder, and Attention U-Net on the BraTS dataset with patch-based training and mixed precision. Final validation Dice: 0.8256 with Attention + EfficientNet.

Medical AIComputer VisionPyTorch3D U-NetBraTSMONAI
Read post
2025-04-10 · 12 min read

Weather Prediction at Scale: 4,300+ Cities, 90GB, One Model Each

How I built a city-specific weather forecasting pipeline training 4,300+ independent XGBoost models on 10 years of historical data—lessons in data organization, pipeline automation, and when local models beat global ones.

Data EngineeringXGBoostTime SeriesMLOpsScalable ML
Read post