Prompt Engineer
Summary
Designs and optimizes prompts for LLMs (GPT, Claude, Gemini) and builds RAG pipelines using LangChain/LlamaIndex to deliver tailored AI outputs for enterprise domains like legal, medical, and finance.
Responsibilities:
• Design, optimize, and iterate prompts for LLMs including GPT, Claude, and Gemini to achieve high-quality outputs
• Build RAG (Retrieval-Augmented Generation) pipelines using LangChain or LlamaIndex for enterprise applications
• Develop evaluation frameworks to measure prompt performance, cost, and latency
• Collaborate with domain experts to tailor outputs for industries like legal, medical, and finance
• Troubleshoot LLM limitations and implement structured output solutions using JSON/YAM
Requirements
• Bachelor's Degree in Computer Science, AI, or related discipline
• 2+ years of hands-on experience working with LLMs and prompt engineering
• Proficient in Python; experience with LangChain, LlamaIndex, and LLM APIs (OpenAI, Anthropic, Google)
• Strong understanding of prompt design techniques (chain-of-thought, few-shot, structured outputs)
• Familiarity with vector databases (Pinecone, Weaviate, Milvus) is an advantage
• Portfolio of prompt engineering projects required