Staff AI Engineer
Core
Architect and deploy end-to-end AI pipelines for construction technical documents, submittals, schedules, and product cross-referencing using RAG, OCR, and multi-modal models.
Role type
Staff AI Engineer (LLM & RAG)
Builds
Document intelligence pipelines, semantic search, embeddings, reranking systems, and generative workflows for AutoQuote.
Domain
Construction technology (AEC) and PropTech
Deliverable
production ML models | product features
Required skills
LLMs, RAG architectures, prompt engineering, vector databases, system design, SQL, Node.js/TypeScript or Python, Docker, AWS, OCR, multi-modal LLMs
Preferred skills
AEC/PropTech domain knowledge, PHP, PyTorch/TensorFlow, traditional ML, mentoring
Technologies
AWS, Docker, MySQL, PostgreSQL, PyTorch, Python, TensorFlow, TypeScript, NodeJS, Spark, LLM, MLOps, RAG, Embedding Models, Fine-tuning
Responsibilities
Architect and deploy end-to-end AI pipelines for construction documents; make and defend build-versus-buy decisions; define design standards for retrieval and RAG patterns; build document intelligence pipelines using OCR and multi-modal models; develop semantic search and reranking systems; own evaluation strategy including golden datasets and regression testing; monitor production output for drift and enforce data governance; integrate AI services into AWS microservices; implement guardrails and continuous learning loops; partner with stakeholders on technical roadmaps.
Seniority
Staff, hands-on IC with mentorship