Applied AI Engineer

Role overview This position focuses on applied AI for real estate market intelligence: extracting structure from messy public sources, retrieving across market and geospatial context, and producing drafts a human reviewer can trust. Evaluation, grounding, and provenance are treated as first-class concerns, so every model output must be checkable before it informs a downstream decision.

Responsibilities - Build production LLM pipelines for extraction, classification, summarization, and draft report sections, grounded in cited sources. - Design retrieval and context assembly over structured market data, registries, and geospatial layers. - Define evaluations and regression checks so model or prompt changes do not silently degrade quality. - Instrument cost, latency, and failure modes, keeping human review in the loop for any output that informs a client decision. - Partner with data engineers and domain analysts so AI outputs land in the same provenance and confidence model as every other figure.

Requirements - Track record of taking LLM or ML features to production, beyond notebooks or prototypes. - Strong Python skills and comfort with APIs, data contracts, and production debugging. - Obsession with grounding, citation, and failure cases, and refusal to trust a fluent answer without evidence. - Ability to explain quality-versus-cost-versus-latency trade-offs to both engineers and domain experts.