Does this skill help with initial model research?

While it can assist with training scripts, its primary focus is on production engineering, MLOps, and the operational aspects of deploying and maintaining models.

Can this skill help reduce LLM API costs?

Yes, it includes specific patterns for token counting, response caching, and provider abstraction to help track and minimize LLM expenses.

How does it handle RAG implementation?

It provides comprehensive guidance on vector database selection (Pinecone, Qdrant, etc.), document chunking strategies, and retrieval optimization like reranking.

What tools are included in the MLOps patterns?

The skill covers industry-standard tools including MLflow, Kubeflow, Feast for feature stores, and containerization with Docker and Kubernetes.

Senior ML Engineer

Name: Senior ML Engineer
Author: zhangzhang-111-i

byzhangzhang-111-i

0•

Ciencia de Datos y ML

Productionizes machine learning models, builds MLOps pipelines, and implements robust LLM application architectures.

The Senior ML Engineer skill equips Claude with specialized knowledge for the operational phase of the machine learning lifecycle. It moves beyond initial research to focus on production concerns such as containerized model deployment, MLOps infrastructure setup using MLflow and Kubeflow, and the implementation of enterprise-grade RAG systems. The skill provides proven patterns for LLM integration—including provider abstraction, cost management, and retry logic—alongside sophisticated monitoring tools for detecting data drift and performance degradation in live environments.

Características Principales

01End-to-end MLOps pipeline setup with feature stores and experiment tracking

02Production-grade model deployment templates for Docker and Kubernetes

030 GitHub stars

04Real-time model monitoring and statistical drift detection workflows

05LLM API integration patterns with cost optimization and provider failover

06Advanced RAG system architectures with vector database integration and chunking strategies

Casos de Uso

01Building a scalable Retrieval-Augmented Generation (RAG) pipeline for document search

02Transitioning a research model to a high-concurrency production API with monitoring

03Establishing automated retraining loops triggered by model performance decay

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add zhangzhang-111-i/claude-skills111 senior-ml-engineer

For use in Claude.ai and ChatGPT

Características Principales

01End-to-end MLOps pipeline setup with feature stores and experiment tracking

02Production-grade model deployment templates for Docker and Kubernetes

030 GitHub stars

04Real-time model monitoring and statistical drift detection workflows

05LLM API integration patterns with cost optimization and provider failover

06Advanced RAG system architectures with vector database integration and chunking strategies

Casos de Uso

01Building a scalable Retrieval-Augmented Generation (RAG) pipeline for document search

02Transitioning a research model to a high-concurrency production API with monitoring

03Establishing automated retraining loops triggered by model performance decay

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add zhangzhang-111-i/claude-skills111 senior-ml-engineer

For use in Claude.ai and ChatGPT