AI Engineer (Assistant)
Build and ship production agentic AI workflows for complex real estate and built-world processes. The role combines product engineering, applied AI, customer collaboration, workflow orchestration, evaluation, and reliable user-facing experiences.
About the job
Responsibilities
- 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, 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 from backend workflow logic through user-facing review, approval, and collaboration surfaces.
- Design context strategies for documents, prior decisions, domain constraints, tool outputs, and user intent.
- Build retrieval, extraction, structured-output, and tool-calling flows for expert users.
- Create evaluations for document understanding, grounded reasoning, workflow completion, visual QA, accuracy, latency, and customer usefulness.
- Inspect traces, debug failures, improve prompts and workflows, and convert customer feedback into measurable system improvements.
- Partner with AI and infrastructure teams on agent reliability, observability, evaluation, and developer velocity.
- Build inspectable, explainable, and trusted AI systems.
Requirements
- Strong product-minded software engineering background with production systems used by real users.
- Experience building with LLM APIs, agent frameworks, structured outputs, tool calling, retrieval-augmented generation, document processing, or workflow systems.
- Proficiency with Python and modern backend systems, with the ability to work across the stack.
- Ability to translate ambiguous customer problems into reliable products.
- Understanding of evaluations, traces, regressions, edge cases, latency, cost, and user trust.
- Comfortable collaborating with domain experts and learning complex industries.
- Strong product judgment and an ability to make complex AI behavior understandable.
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 domains.
- Experience designing human-in-the-loop systems, review workflows, confidence surfaces, or expert feedback loops.
- Experience turning customer-specific workflows into reusable product capabilities.
Compensation and Benefits
- Meaningful equity.
- Significant ownership of customer and product problems.
- Opportunity to work on agentic AI, product engineering, and institutional real estate.
Skills
Python, LLM APIs, Agent Frameworks, Structured Outputs, Tool Calling, RAG, Document Processing, Workflow Systems, LangGraph, LangChain, Temporal, Vector Databases, Multimodal Models, Observability
Similar jobs
ML Engineering jobs
Build
New York, NY
Build modular AI operations and evaluation systems that power complex real estate workflows. The role focuses on improving output quality, defining correctness with domain experts, and reducing human review while maintaining high standards.
Build
New York, NYBuild and operate Dougie, an agentic AI system that executes workflows, evaluates its own performance, retains institutional context, and improves in production. The role requires experience deploying unattended agentic systems and engineering reliable memory, retrieval, orchestration, and feedback loops.
Mintlify
San Francisco, CA
Build and own customer-facing AI products from experimentation through production, including reliable agents, evaluation systems, APIs, interfaces, and infrastructure. Requires at least four years of software development experience and deep production experience with language-model systems.
PathAI
Boston, MADevelop and deploy machine learning models for biomedical research and AI products, collaborating with scientific, engineering, and product teams. Requires an advanced quantitative degree, substantial ML experience, Python proficiency, and experience bringing models into production or research applications.
Coalition Security
United StatesBuild and operate LLM-powered agents that automate business workflows, integrating systems of record through MCP and validating behavior with structured evaluations. Requires 5+ years of software development experience, strong Python and SQL, and hands-on experience shipping agents to production.