AI Engineer - Agent Capabilities
Jobverse.ioAbout the role
Build is creating an agentic AI stack for the built world, helping institutional real estate teams automate complex development and acquisitions workflows. The AI Engineer will build and ship production agentic workflows, working with customers, domain experts, designers, and engineers to transform complex real estate processes into reliable AI-powered product experiences.
Responsibilities
Design and ship production AI workflows for real estate design, acquisitions, diligence, planning, and project execution
Work directly with customers and internal experts to map complex workflows into software systems with clear inputs, outputs, edge cases, and success criteria
Build agents that reason across leases, zoning documents, site plans, drawings, financial models, market comps, investment memos, permits, emails, and project history
Own full-stack product features end to end, from backend workflow logic to user-facing review, approval, and collaboration surfaces
Design context strategies that help agents use the right documents, prior decisions, domain constraints, tool outputs, and user intent at the right time
Build retrieval, extraction, structured-output, and tool-calling flows that are robust enough for expert users
Create evals for document understanding, grounded reasoning, workflow completion, visual QA, accuracy, latency, and customer usefulness
Inspect traces, debug failures, improve prompts and workflows, and turn customer feedback into measurable system improvements
Partner with the core AI and infrastructure team to improve agent reliability, observability, evaluation, and developer velocity
Raise the product quality bar for AI systems that need to be inspectable, explainable, and trusted
Responsibilities
- Design and ship production AI workflows for real estate design, acquisitions, diligence, planning, and project execution
- Work directly with customers and internal experts to map complex workflows into software systems with clear inputs, outputs, edge cases, and success criteria
- Build agents that reason across leases, zoning documents, site plans, drawings, financial models, market comps, investment memos, permits, emails, and project history
- Own full-stack product features end to end, from backend workflow logic to user-facing review, approval, and collaboration surfaces
- Design context strategies that help agents use the right documents, prior decisions, domain constraints, tool outputs, and user intent at the right time
- Build retrieval, extraction, structured-output, and tool-calling flows that are robust enough for expert users
- Create evals for document understanding, grounded reasoning, workflow completion, visual QA, accuracy, latency, and customer usefulness
- Inspect traces, debug failures, improve prompts and workflows, and turn customer feedback into measurable system improvements
Qualifications
- The candidate should be able to build robust retrieval and extraction flows and create evaluations for grounded reasoning and accuracy.
- Experience in mapping complex domain workflows into software systems with clear success criteria is required.
Skills mentioned
About Jobverse.io
Go from 'Job Found' to 'Applied' in under 60 seconds with Jobverse.io.