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
