Tenzaa's Tech Blog
This site is dedicated to sharing IT-related technologies.
Implementing a Zero-Downtime ML Model Serving Architecture with Go-Kit MLflow and Docker Swarm Implementing a Zero-Downtime ML Model Serving Architecture with Go-Kit MLflow and Docker Swarm
The existing machine learning model serving infrastructure was a significant source of operational friction. Each model
2023-10-27
Implementing Full-Stack Traceability in an MLOps Platform Using Redux Middleware and OpenTelemetry Implementing Full-Stack Traceability in an MLOps Platform Using Redux Middleware and OpenTelemetry
The operational visibility into our ML model serving platform was effectively zero. When a user reported that a predicti
2023-10-27
Declarative Provisioning of MLflow Environments Using a Custom Crossplane API for MongoDB Backends Declarative Provisioning of MLflow Environments Using a Custom Crossplane API for MongoDB Backends
The operational friction in our machine learning lifecycle was becoming untenable. Our data science teams were either pi
2023-10-27
Optimizing Polyglot MLOps CI Pipelines by Caching Babel Artifacts for Azure AKS Deployments Optimizing Polyglot MLOps CI Pipelines by Caching Babel Artifacts for Azure AKS Deployments
Our MLOps pipeline feedback loop was broken. A single commit to our model’s inference service, a Node.js application, tr
2023-10-27
Implementing a Real-Time Feature Engineering Pipeline with Kotlin, Pulsar, and Kubeflow Implementing a Real-Time Feature Engineering Pipeline with Kotlin, Pulsar, and Kubeflow
Our MLOps platform hit a wall. The core problem was feature engineering. Batch ETL jobs running nightly were too slow fo
2023-10-27
Automating a Cross-Cloud RAG System with Weaviate on GCP and AWS Lambda via CircleCI Automating a Cross-Cloud RAG System with Weaviate on GCP and AWS Lambda via CircleCI
Our RAG prototype, born in a Jupyter Notebook, worked. It could ingest documents, embed them, and answer questions with
2023-10-27
2 / 3