About the role
Meramia Technologies is seeking an experienced AI/ML product leader to bridge engineering of AI harnesses with on-site teams like project managers and field engineers. You will define harness workflows, integrate LLM/vision models with project records, and stand up agents with evaluators to ensure accuracy and safety on live sites.
You will visit construction sites, gather input from managers and subcontractors, and articulate bottlenecks before issuing tickets.
Set the sequence for field-capture processing, plan parsing, submittal review, cost, progress and identify the current harness problem. Specify developer-facing and internal harnesses that bind LLMs and vision-language models to the project record to prevent hallucinations. Stand up agents that can flag hazards, follow deliveries, check builds, or draft change orders with evals attached. Go to site and talk to project managers, superintendents and subcontractors, documenting bottlenecks before writing tickets. Own the evals for accuracy, safety and reliability where outputs affect money or safety. Collaborate with sales and support to measure hours saved and risk reduction, not just claim it. Three or more years running AI or ML products: agent architectures, retrieval, computer vision, and an eval harness you have actually used. The construction lifecycle — pre-construction, bid, schedule, execute, handover — and the tools the trades already live in: Procore, Autodesk Construction Cloud, Primavera P6, Revit, OpenSpace. A plan for unstructured site data: photographs, 360 scans, drone footage, PDF specs, BIM metadata. Four or more years of product work in B2B software, PropTech, ConTech, or developer infrastructure. Interviews, prototypes, a backlog you will defend, and the ability to talk to researchers, engineers, designers and a superintendent in the same week.