skills.rest
slantview
slantviewCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

ml-engineer

Implements ML pipelines for serving, feature engineering, and monitoring with TensorFlow or PyTorch deployment.

1|1|Updated Aug 5, 2025
Search Tags:#monitoring#mlops#machine learning#feature engineering#production deployment#model serving
One-click install
npx skills add https://github.com/slantview/claude --skill ml-engineer-slantview
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ml-engineer
Source: https://github.com/slantview/claude/tree/main/skills/ml-engineer
Command: npx skills add https://github.com/slantview/claude --skill ml-engineer-slantview

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) and scripts (resource) components.

What problem does it solve?

This Skill streamlines the complex process of integrating machine learning models into production environments, ensuring reliable serving, feature engineering, and ongoing monitoring.

Core Features & Use Cases

  • Model Serving: Deploy models using frameworks like TorchServe, TensorFlow Serving, or ONNX Runtime.
  • MLOps Integration: Implement best practices for versioning, A/B testing, and monitoring ML systems.
  • Use Case: Deploy a newly trained recommendation model to a production API, set up A/B testing for two model versions, and configure monitoring for prediction drift.

Quick Start

Use the ml-engineer skill to deploy the latest version of the fraud detection model to production.

Frequently Asked Questions about ml-engineer

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

FAQPage Schema
How do I deploy machine learning models to a production API?▼

Deploy machine learning models to production using serving frameworks like TorchServe, TensorFlow Serving, or ONNX Runtime to expose inference endpoints via API.

What is the best way to set up A/B testing for ML model versions?▼

Set up A/B testing for ML model versions by implementing MLOps best practices for versioning, allowing you to compare prediction performance between two deployed model iterations.

How do I configure monitoring for prediction drift in production ML systems?▼

Configure monitoring for prediction drift by implementing operational monitoring systems that track model performance and data distribution shifts in real-time or batch inference pipelines.

Can I use this for both real-time and batch inference systems?▼

Yes, you can use this to implement both real-time and batch inference systems, addressing operational requirements for continuous predictions and scheduled data processing workflows.

How do I handle feature engineering in production ML pipelines?▼

Handle feature engineering in production ML pipelines by implementing standardized processing logic to transform raw data into model-ready features consistently during deployment.

Does this support deploying TensorFlow and PyTorch models?▼

Yes, it supports deploying TensorFlow and PyTorch models by addressing specific framework requirements for production serving and utilizing documentation retrieval for library compatibility.

Related Skills

Explore More Software Engineering Skills→
BoraPerusicBoraPerusic

ml-engineer

Automate design and deployment of production ML systems across PyTorch and TensorFlow.

Community
Advanced
nirukk52nirukk52
1

dev-log-monitoring

Monitor Encore.ts and SvelteKit logs to diagnose drift and verify run events.

Community
Advanced
doanchienthangdevdoanchienthangdev
4

mlops

Automate ML lifecycle management with CI/CD, experiment tracking, and model registry.

Community
Advanced
1thirteeng31thirteeng3

modal-serverless-gpu

Deploy ML workloads to Modal's serverless GPU cloud with auto-scaling.

Community
Advanced