Prompt Engineer

Role Overview 

Design and optimize prompts for large language models to build robust AI applications. Develop LLM-powered solutions using LangChain and vector databases.  

Responsibilities 

• Design, test, and optimize prompts for LLMs to achieve desired outputs and behaviors 
• Build and deploy LLM applications using LangChain and related frameworks 
• Implement RAG (Retrieval Augmented Generation) systems with vector databases 
• Develop prompt templates, chains, and agents for various use cases 
• Evaluate and benchmark LLM performance across different prompting strategies 
• Collaborate with engineers and product teams to integrate LLM solutions 

Requirements 

• Bachelor's degree in Computer Science, Engineering, Linguistics, or related field 
• Proven experience in LLM prompting and prompt engineering techniques 
• Strong hands-on experience with LangChain framework 
• Proficiency with vector databases (Pinecone, Weaviate, ChromaDB, FAISS) 
• Understanding of LLM capabilities, limitations, and best practices 
• Experience with OpenAI, Anthropic, or other LLM APIs 
• Proficiency in Python 

Preferred 

• Experience with prompt optimization techniques (few-shot, chain-of-thought, ReAct) 
• Knowledge of embedding models and semantic search 
• Familiarity with LLM evaluation frameworks 
• Understanding of agentic workflows and tool-using LLMs 
• Experience with MLOps and production deployment