skills.rest
fakhriaditiarahman
fakhriaditiarahmanCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

llm-ops-engineer

Deploy, fine-tune, and monitor LLMs with vLLM, TGI, and Ollama.

1|Updated Jan 20, 2026
Search Tags:#monitoring#rag#fine-tuning#ai infrastructure#llmops#llm deployment
One-click install
npx skills add https://github.com/fakhriaditiarahman/Your-Skill-Agent --skill llm-ops-engineer
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: llm-ops-engineer
Source: https://github.com/fakhriaditiarahman/Your-Skill-Agent/tree/main/.agent/skills/llm-ops-engineer
Command: npx skills add https://github.com/fakhriaditiarahman/Your-Skill-Agent --skill llm-ops-engineer

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill streamlines the complex process of deploying, fine-tuning, and monitoring Large Language Models (LLMs), ensuring robust and efficient AI infrastructure.

Core Features & Use Cases

  • LLM Deployment: Orchestrates model serving using frameworks like vLLM, TGI, and Ollama.
  • RAG Architecture: Designs and implements Retrieval-Augmented Generation pipelines.
  • Fine-tuning: Manages PEFT/LoRA fine-tuning workflows and model evaluation.
  • Monitoring & Optimization: Tracks performance, costs, and latency for LLM applications.
  • Use Case: Deploy a fine-tuned LLM for customer support, set up a RAG pipeline to access internal documentation, and monitor its performance and cost in real-time.

Quick Start

Use the llm-ops-engineer skill to deploy the 'llama3-8b' model using vLLM.

Frequently Asked Questions about llm-ops-engineer

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

FAQPage Schema
How do I deploy an LLM using vLLM?▼

To deploy an LLM using vLLM, use this Skill to orchestrate model serving and manage the deployment infrastructure. It supports frameworks like vLLM, TGI, and Ollama for efficient LLM deployment and operational management.

What is the best way to set up a RAG pipeline for internal documentation?▼

The best way to set up a RAG pipeline is by using this Skill to design and implement Retrieval-Augmented Generation architecture integrated with vector databases. This enables your LLM to access and retrieve internal documentation efficiently.

How does PEFT or LoRA fine-tuning work for large language models?▼

PEFT and LoRA fine-tuning work by managing parameter-efficient fine-tuning workflows and model evaluation within your LLM infrastructure. This Skill handles these workflows to adapt large language models for specific tasks like customer support.

Can I monitor LLM application performance, costs, and latency in real-time?▼

Yes, you can monitor LLM application performance, costs, and latency in real-time. This Skill tracks these operational metrics to ensure robust AI infrastructure management and optimize overall LLM operational efficiency.

Do I need specific serving technologies to manage AI infrastructure?▼

Yes, managing AI infrastructure requires expertise in specific LLM serving technologies and frameworks. This Skill utilizes vLLM, TGI, and Ollama alongside evaluation metrics to ensure robust AI system management and deployment.

Related Skills

Explore More Software Engineering Skills→
ancolemanancoleman
503

model-serving

Deploy LLM and ML models for production inference with vLLM, TensorRT-LLM, Ollama, and BentoML.

Community
Advanced
helix4uhelix4u

serving-llms-vllm

Serve LLMs with vLLM for high-throughput, low-latency inference.

Community
Advanced
camoneartcamoneart
5

rag-implementation

Implement RAG systems with vector databases and retrieval strategies.

Community
Advanced
LaurentPRAT-DBLaurentPRAT-DB

databricks-genai

Develop and deploy Generative AI applications on the Databricks platform.

Community
Advanced