Build Technologies
AI Engineer - Assistant Capabilities
About this role
Build is hiring an AI Engineer to develop production-grade agentic workflows that automate complex real estate development and acquisitions processes. You'll design and ship AI systems that help institutional real estate teams reason across documents, drawings, and financial models while keeping human experts in control and informed.
What you'll do
- Design and ship production AI workflows for real estate design, acquisitions, diligence, planning, and project execution
- Work with customers and domain experts to map complex workflows into software systems with clear inputs, outputs, and success criteria
- Build agents that reason across leases, zoning documents, site plans, drawings, financial models, and project history
- Own full-stack product features from backend workflow logic to user-facing review and collaboration surfaces
- Design context strategies and retrieval flows that help agents use the right information at the right time
- Create evaluations and debug failures to improve agent reliability, accuracy, latency, and customer usefulness
What they're looking for
- Production AI/LLM systems and agentic workflows
- Context engineering and prompt optimization
- Document intelligence and visual reasoning
- Retrieval-augmented generation (RAG) and structured outputs
- Full-stack product development
- Evaluation design and observability
- Python or similar backend languages
- Tool-calling and workflow orchestration
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
Build Technologies
Build Technologies develops core infrastructure and agentic AI systems designed for real estate and built-world enterprises operating in production environments. The company is hiring AI engineers to build agent runtimes, evaluation systems, retrieval layers, and observability platforms that power reliable, scalable AI workflows.
View all jobs at Build TechnologiesLikely interview questions
- Walk us through a production AI system you've built—how did you handle ambiguity, define success metrics, and iterate based on real user feedback?
- Describe your experience designing evaluations for LLM-based systems. How do you balance automated metrics with human judgment?