MLOps & Cloud
EEG data pipeline: raw time series to Django Ninja API
Scale academic EEG scripts to production. Build a GDPR-compliant ingestion engine with Django Ninja and Zarr that cuts query latency to 18 ms.
Blog
Agentic AI, MLOps & Cloud Engineering
Production-grade deep-dives on AI agents, MLOps on AWS, document intelligence - and what cognitive science teaches us about building better AI.
Cognitive Science & AI
Hippocampal Indexing: Rebuilding AI Memory Systems
Discover how hippocampal indexing solves vector memory collisions in AI agents. Explore bio-inspired memory architectures to scale your production reasoning.
Document AI
Document AI Pipeline on AWS: From PDF to Data
Build a production Document AI pipeline on AWS with Textract, Bedrock Converse, and Step Functions. Cut OCR bills by 80% and deploy clean typed …
Agentic AI
Tool calling benchmark: the provider is in the score
Fresh tau2 tool calling benchmark data (Oct 1, 2026): a 0.006 USD task next to a 1.28 USD one. How to read the board …
MLOps & Cloud
SageMaker async inference: the scale-to-zero trap
Cut idle SageMaker async inference spend without stranding requests. Build a wake-up policy, durable completion handling, and an honest cost model.
MLOps & Cloud
fMRI data pipeline: bounded-memory BIDS to research API
Build an fMRI data pipeline that tracks discarded scans, bounds voxel reads and gates research API access. See the code and capacity math.