Senior AEO Research Engineer
Lead research and development of novel benchmarking techniques measuring LLM citation behaviors, answer generation, and prompt win-rates across ChatGPT, Claude, Perplexity, and Gemini.
Key Responsibilities
- Develop distributed prompt-testing harnesses across frontier LLM APIs and web-grounded inference models.
- Analyze answer engine retrieval patterns (RAG) and reverse-engineer citation weighting models.
- Design scoring algorithms powering the core ReachHub Brand Score and AI Visibility Index.
- Collaborate with data engineers to scale prompt evaluation across millions of daily entity mentions.
Requirements & Qualifications
- 4+ years experience in Python, PyTorch/vLLM, or production LLM application pipelines.
- Deep conceptual and mathematical understanding of embeddings, vector databases, and RAG architectures.
- Familiarity with modern AI search engines, crawler behaviors, and synthetic search evaluation.
- Track record of shipping production AI software or publishing high-impact AI/NLP research.