AI & LLM Integration Engineer

Role overview Design and deliver AI-powered agents and automated workflows for customer-facing applications. The role combines workflow and retrieval-augmented generation (RAG) design with software integration, then improves model output quality, response speed, and operating cost.

Responsibilities - Create and deploy intelligent operational workflows and RAG agents. - Integrate AI models into applications designed to serve customers at scale. - Measure and improve the quality, latency, and cost of large language model (LLM) outputs.

Requirements - Practical experience with Python, LLM APIs, and frameworks such as LangChain. - Familiarity with vector databases such as Pinecone or Chroma and with semantic search. - Understanding of software engineering practices, API design, and cloud deployments.