AI / LLM Engineer
Confirmed on the employer's own hiring board on Oct 31, 2026. First seen by Alion on Oct 30, 2026.
Requirements
About the Role We are looking for an AI/LLM Engineer to build and own the intelligence layer of ACORDAI an AI-native insurance SaaS platform. You will design RAG pipelines, build the AI Copilot, and develop agentic workflows that automate complex insurance processes.
Responsibilities Build and maintain RAG pipelines for document ingestion and retrieval. Extract structured coverage data from forms and documents. Develop the AI Copilot for agents, underwriters, and claims handlers. Design agentic workflows using LangGraph for multi-step insurance automation. Build risk scoring models combining structured data with LLM-derived signals. Write, version, and optimize prompts for OpenAI and other frontier models. Create evaluation pipelines to measure accuracy, latency, and reliability. Monitor AI features in production and iterate based on quality metrics. Tech Stack LLMs: OpenAI GPT-4o, Anthropic Claude Orchestration: LangChain, LangGraph Vector Search: pgvector, Pinecone Backend: Python, FastAPI Database: PostgreSQL, Redis Infrastructure: AWS / Azure, Docker Requirements 3+ years building LLM-powered production applications. Hands-on experience with LangChain and/or LangGraph. Strong Python skills and experience with REST APIs. Experience designing and deploying RAG systems. Familiarity with vector databases and semantic search. Solid understanding of prompt engineering and context management. Experience building LLM evaluation pipelines. Nice to Have Experience in insurance, fintech, or legal tech. Familiarity with structured PDF data extraction. Knowledge of fine-tuning or open-source model deployment.