AI Engineer - Assistant Capabilities

Build Technologies • London, New York

1d • $125,000 - $225,000 • Hybrid

About The Position

Build is seeking an AI Engineer to build agentic workflows for institutional real estate teams, automating complex development and acquisitions. The role involves transforming ambiguous workflows into reliable product experiences by working with customers, domain experts, designers, and engineers. The focus is on the intersection of product engineering and applied AI, including long-running agents, context engineering, document intelligence, visual reasoning, workflow orchestration, human-in-the-loop review, evals, observability, and creating trustworthy AI product surfaces. This is a production-focused role, not research or demo-building, with ownership of customer outcomes and defining AI-native product engineering in the built world.

Requirements

• Strong product-minded software engineer who has shipped production systems used by real users.
• Experience building with LLM APIs, agent frameworks, structured outputs, tool calling, RAG, document processing, or workflow systems.
• Comfortable with Python and modern backend systems, and ability to move across the stack when needed.
• Ability to take a vague customer problem, ask the right questions, identify the workflow, and turn it into a product that works.
• Care about agent quality beyond prompts: evals, traces, regressions, edge cases, latency, cost, and user trust.
• Enjoy working with domain experts and learning the details of complex industries.
• Ability to move fast but distinguish a compelling demo from a reliable production system.
• Good product taste and care about making complex AI behavior understandable to users.

Nice To Haves

• Experience with LangGraph, LangChain, Temporal, workflow engines, vector databases, reranking, document AI, multimodal models, or agent observability tools.
• Experience building AI products in real estate, construction, infrastructure, finance, legal, insurance, logistics, or other expert-heavy workflows.
• Experience designing human-in-the-loop systems, review workflows, confidence surfaces, or expert feedback loops.
• Experience turning customer-specific workflows into reusable product capabilities.

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.

Benefits

• Real ownership: Own meaningful customer and product problems end to end with autonomy and accountability.
• Steep learning curve: Build at the frontier of agentic AI, product engineering, and institutional real estate with direct feedback loops.
• Exceptional teammates: Work with clear thinkers who execute with intensity and care deeply about the company.
• Meaningful equity: Ownership in the work is matched with ownership in the company.
• A chance to shape the physical world: Software accelerates real projects in infrastructure, energy, industrial, housing, and more.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Education Level: No Education Listed