skills.rest
bcastelino
bcastelinoCOMMUNITY
Explore all skills by this author →
Website𝕏@cas7elinoGitHub

ml-engineer

Design production ML system architectures for scalable model serving.

2|Updated Feb 6, 2026
Search Tags:#mlops#machine learning#model deployment#feature store#model serving#ml infrastructure#production ml
One-click install
npx skills add https://github.com/bcastelino/agent-skills-kit --skill ml-engineer-bcastelino
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ml-engineer
Source: https://github.com/bcastelino/agent-skills-kit/tree/main/skills/ml-engineer
Command: npx skills add https://github.com/bcastelino/agent-skills-kit --skill ml-engineer-bcastelino

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides expert guidance and capabilities for building, deploying, and managing production-grade machine learning systems and infrastructure.

Core Features & Use Cases

  • ML System Design: Architect scalable and reliable ML pipelines, serving infrastructure, and feature stores.
  • Production Deployment: Implement best practices for deploying models to various environments (cloud, edge).
  • MLOps Integration: Automate training, monitoring, and retraining processes.
  • Use Case: Deploy a real-time recommendation engine that handles 100,000 predictions per second, ensuring high availability and low latency.

Quick Start

Design an ML system architecture for a real-time recommendation engine capable of handling 100,000 predictions per second.

Frequently Asked Questions about ml-engineer

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I design ML infrastructure for a high-throughput model serving system?▼

To deploy production ML systems, you must architect scalable serving infrastructure and feature stores, implement MLOps automation for training and monitoring, and optimize performance to ensure low latency and high availability for real-time inference.

What is the best way to automate MLOps for model retraining and monitoring?▼

Automating MLOps involves integrating automated training, monitoring, and retraining processes into your ML infrastructure, ensuring scalable and reliable production ML systems that adapt to data changes without manual intervention.

How do I architect a feature store for production machine learning pipelines?▼

Architecting a feature store for production ML pipelines involves designing centralized infrastructure that serves consistent features for both training and real-time inference, ensuring scalable and reliable model deployment across various environments.

Can I use this approach for deploying machine learning models to edge environments?▼

Yes, this approach supports deploying machine learning models to edge environments by implementing production deployment best practices, ensuring the ML infrastructure can deliver scalable and reliable inference outside traditional cloud environments.

How do I optimize ML system performance for 100,000 predictions per second?▼

Optimizing ML system performance for 100,000 predictions per second requires architecting scalable ML infrastructure and applying performance optimization techniques to the model serving layer to minimize latency and ensure high availability.

Related Skills

Explore More Software Engineering Skills→
angryracoonangryracoon

data360-prepare

Prepare Salesforce Data Cloud ingestion assets for raw source data.

Community
Advanced
KentoShimizuKentoShimizu
7

mlops-monitoring-drift

Detect data drift, concept drift, and quality degradation in production ML pipelines.

Community
Advanced
bomberoxenviosdosruedasbomberoxenviosdosruedas

agency-devops-automator

Automate DevOps workflows with Terraform, GitHub Actions, Kubernetes, and Prometheus.

Community
Advanced
tangzheng202202tangzheng202202
1

modal-serverless-gpu

Deploy GPU-based ML workloads on a serverless cloud platform.

Community
Advanced