Applied Research Engineer

Role overview An Applied Research Engineer position is open on a Platform R&D team building spatial AI for residential design. The role sits between research and product, taking machine learning models that have already shown promise in research and turning them into reliable, user-facing capabilities inside a home design product. Work centers on a generative floor plan engine that is already a core workflow.

Responsibilities - Build the component layer around a layout synthesis engine, including a documented API contract, a callable service, and an automated evaluation gate that runs on every change. - Convert model retraining into a one-command job with built-in benchmarks and shareable results. - Own latency and cost budgets for learned capabilities and improve reproducibility across the existing codebase. - Extend core research into new capabilities such as multi-story plans and real-time editing. - Partner with infrastructure engineers on MLOps and deployment, and mentor researchers and interns on engineering practices. - Communicate work through weekly status updates, clear pull requests, and design notes ahead of major changes.

Requirements - 5+ years of professional software development, including at least 2 years training and shipping ML models to real users. - End-to-end ownership of at least one model: data preparation, training, evaluation, serving, and user-facing integration. - Fluency in Python and PyTorch. - Experience with geometric or structured data such as floor plans, CAD or BIM, graphs, or 2D and 3D geometry. - Built or maintained an evaluation harness or benchmark used to gate changes. - Packaged a model behind an API and owned its latency and cost. - Master's degree in computer science, machine learning, or a related field, or equivalent shipped work. - Comfort working remotely on US Eastern hours.

Nice to have - Background in architecture or building, including AEC software work. - Experience with constraint solvers like OR-Tools CP-SAT, optimization, or generative models for layouts and floor plans. - Plugin or tooling work in Rhino, Grasshopper, or Revit, or experience with Hugging Face, experiment tracking, and cloud model serving on AWS or Modal, plus publications or open-source contributions.

Benefits and work setup - Fully remote company with regular team meet-ups in US hubs. - Competitive salary with significant equity. - Comprehensive medical, dental, and vision coverage; flexible PTO; meaningful parental leave. - Short- and long-term disability plans, 401(k), home office stipend, and ongoing learning and development support.