Research Engineer (Spatial AI)

TL;DR

Research Engineer (Spatial AI): Conducting foundational research in spatial reasoning for residential construction, developing novel models at the intersection of reinforcement learning, computer vision, LLMs, and 3D geometry with an accent on architectural structure understanding and geometric constraints. Focus on designing end-to-end LLM pipelines, multimodal training, RL-based generative design, and construction-domain benchmarks.

Location: Remote (United States) for U.S.-based full-time employees

Company

VC-backed startup changing how new homes are designed and built, with products shipped for Autodesk, Electronic Arts, Nike, and Apple.

What you will do

• Design and conduct original research in spatial reasoning for residential construction, developing models for architectural structure, spatial relationships, and geometric constraints.
• Design LLM training and fine-tuning pipelines using domain-specific datasets from architectural drawings, building codes, and construction documentation.
• Apply computer vision to extract semantic structure from inputs and build multimodal pipelines linking visual and textual building data.
• Develop RL-based generative design and RAG systems grounded in construction knowledge bases to reduce hallucinations.
• Define benchmarks, build datasets, and establish eval pipelines for real homebuilding tasks; research foundation models and fine-tuning approaches.
• Deliver integration-ready research outputs including model artifacts, pipelines, and APIs, partnering with Prototyping Engineer for deployment.

Requirements

• 5+ years professional software engineering, 2+ years on LLM development, fine-tuning, or applied ML in production
• Hands-on with model training frameworks (HuggingFace Transformers, PyTorch) and fine-tuning on domain-specific corpora
• Experience with RAG architectures, vector databases (Pinecone, Weaviate, pgvector), and embedding models
• Experience with 3D modeling, computational geometry, or computer graphics
• Strong Python proficiency across ML ecosystem; React/TypeScript for integration
• Master's in Computer Science, Machine Learning, AI, or related field

Nice to have

• Ph.D., especially in model research and pre-training
• Open-source contributions or published research
• Familiarity with BIM tools (Revit, AutoCAD) or formats (IFC, gbXML)
• Experience with Three.js or equivalent 3D frameworks

Culture & Benefits

• Remote-first since 2018 with flexible hours.
• Competitive salaries with significant equity.
• Comprehensive medical, dental, vision coverage, unlimited PTO, maternity/paternity leave, short/long-term disability, 401K for U.S.-based full-time employees.
• Stipend for home office setup.