ai-engineer - AI Integration Specialist
Integrate LLM APIs, build RAG pipelines, control token costs, and prevent prompt injection attacks
Tags
Updated: 2026-05-09Capabilities
Typical Inputs
Typical Outputs
What this skill does
- select LLM model
- build RAG pipeline
- design prompt
- cache prompts
- trim context
- stream response
- prevent prompt injection
- prevent data leak
- call LLM API
- create vector embedding
- query vector database
- chunk text
- validate input
- filter output
- log prompts
- log responses
- monitor usage
Inputs
- LLM API key
- documents
- vector database
- question
- user message
- traffic estimate
Outputs
- Markdown blueprint file
- code snippet
- model recommendation
- cost analysis
- RAG query result
- AI response
Requirements
- LLM API account
- vector database
- Python runtime
- Node.js runtime
- GPU (for local models)