AI Engineer

CoreStory seeks an AI engineer to develop intelligent systems powering their narrative intelligence platform. The role focuses on building intelligent systems that blend large language models, retrieval architectures, and conversational agents into cohesive, scalable products.

Core Responsibilities

• Designing LLM-powered systems including RAG, chat agents, summarizers, knowledge graph integration
• Building retrieval pipelines using LlamaIndex or LangChain
• Managing vector database implementations (Pinecone, Neo4j, FAISS, Milvus, Weaviate)
• Integrating LLMs (GPT, Claude, Llama, Mistral)
• Deploying scalable AI services
• Developing agentic systems with prompt engineering and tool calling

Required Skills

• 7+ years engineering experience; 3+ years in AI/ML/NLP
• LlamaIndex or LangChain expertise
• Vector database implementation experience
• LLM API integration knowledge
• Python proficiency (FastAPI, Pandas, NumPy)
• RAG patterns, embeddings, tokenization understanding
• Prompt engineering and chat agent architecture familiarity

Tech Stack: LlamaIndex, LangChain, FastAPI, Pinecone, Neo4j, Weaviate, Chroma, Azure Cognitive Search, GPT, Claude, Llama, Mistral, Hugging Face, Docker, Azure, AWS

Preferred: Production AI service deployment, LangGraph, semantic search, hybrid RAG systems, knowledge graphs, document intelligence, multimodal AI, SaaS or early-stage startup background.

Remote US position with flexible, remote-first work environment.