About RealQuant
RealQuant is building the first vertical AI platform for commercial real estate — turning OMs, rent rolls, and financials into structured insights that power underwriting, reporting, and portfolio intelligence.
We’re redefining how deals move from OM → LOI in under 30 minutes by combining institutional real estate expertise with modern AI automation.
Role Overview
You’ll own the AI engine behind our document parsers, data feeds, and underwriting agent — training and fine-tuning multimodal models in Azure AI Foundry to deliver sub-10s parsing and automated deal outputs (LOIs, pitch decks, summaries, and recommended assumptions).
Tech Stack
Core AI Platform : Azure AI Foundry (multimodal)
- Azure ML (training + fine-tune)
- Azure OpenAI
Retrieval & Data : Azure AI Search (vector + hybrid)
pgvectorDatabricks (labeling + ETL)Azure Postgres FlexibleBlob StorageAPIs & Workflows : FastAPI inference services
Azure Durable FunctionsEvent Grid (ingest triggers)Service Bus (optional)API Management (APIM)Ops & Monitoring : App Insights / Monitor
Key Vault (Managed Identity)GitHub Actions CI / CDWhat You’ll Build
Train and fine-tune LLMs + embeddings for OM, Rent Roll, and P&L parsing.Detect and learn document layout patterns to reduce human-in-loop (HITL) review.Build labeled datasets and evaluation benchmarks in Databricks + Azure ML.Integrate 3rd-party market data and create retrieval pipelines via Azure AI Search / pgvector.Develop the AI Underwriting Agent that generates deal summaries, LOIs, pitch decks, and assumptions.Deploy models via Azure ML / Durable Functions with scalable APIs.Optimize inference pipelines for sub-10s end-to-end latency , including preprocessing and write-back to Postgres.Track accuracy, recall, latency & cost with App Insights dashboards; iterate rapidly using Cursor / Claude Code + HITL QA.Expected Outcomes
3+ production-ready parsers (OM, Rent Roll, or P&L) deployed in Azure100+ labeled examples + versioned evaluation datasets≥95% extraction accuracy vs manual baselineAI-generated deal summary & LOI draft live in Excel / webConfidence-scored mappings for Chart of Accounts & unit-type labels with HITL reviewParsing pipeline optimized for sub-10s total latencyExperience
5–7 yrs ML engineering (modeling, evaluation, MLOps)3+ yrs LLM / Document AI (fine-tuning, embeddings, RAG)Hands-on with Azure AI Foundry / Azure ML / OpenAI APIPython + PyTorch / Transformers expertiseExperience with pgvector or AI Search for retrievalFinTech, PropTech, or Data SaaS background a plusFluent Englishownership mindsetoutcome-drivenSelection Process
90-minute async coding / model taskTechnical interviewPaid trial sprint (build a real parser module)Compensation & Setup
Independent Contractor | Hourly DOE
Full-time remote
EST overlapImmediate startLong-term contract with growth potential
How to Apply
Send your GitHub, demo, or portfolio of embedding / LLM work, plus a short note on a model you’ve taken from prototype → production.