Generative AI / LLM Engineer

Job Description

Paxton Consultants is hiring a Generative AI / LLM Engineer to build retrieval-augmented generation pipelines, agentic workflows, and LLM-powered applications using modern foundation models. You will bring ideas to production with a focus on quality, safety, and cost. Key Responsibilities • Design and implement RAG pipelines, including chunking, embedding, retrieval, and re-ranking • Build agentic workflows and tool-using applications with LangChain or similar orchestration frameworks • Work with vector databases and manage knowledge sources and indexing strategies • Create evaluation harnesses to measure relevance, accuracy, hallucination rates, and latency • Implement guardrails, observability, and cost controls for LLM-based services • Collaborate with product and engineering teams to deliver and iterate on AI features This is a contract engagement. This is a remote position open to candidates across the US.