Lead ML Engineer - Computer Vision

About Benchmark Construction Technology Benchmark (formerly BotBuilt, Y Combinator W21) is building the next generation of technology behind American homebuilding. We’re starting with one of the hardest parts of the stack: reliably turning messy, real-world construction plans into structured, usable data. About the role You’ll own and expand our AI-enabled plan ingestion pipeline—from raw PDFs to clean, dependable outputs that power takeoff, design, and downstream automation. What you'll do Architect, build, and deploy ML systems for object detection, segmentation, document understanding, and information extraction from complex building plans Drive R&D across computer vision and/or NLP as applied to construction documents and related data Develop multi-modal approaches that combine vision with language features for document analysis (LLMs/NLP). Familiarity with different RAG methods is a plus Mentor junior engineers and help raise the bar on execution, code quality, and decision-making Ensure systems are reliable, maintainable, testable, and observable in production Qualifications 8+ years of experience in Machine Learning Engineering, with deep focus in computer vision Expert Python skills, with strong experience in PyTorch and FastAPI Proven work with segmentation models, detection frameworks, and OCR/document pipelines Strong image processing fundamentals (OpenCV, geometric transforms, preprocessing, etc.) Comfortable in Linux; hands-on with Docker/containerization for deployment Experience building and maintaining MLops infrastructure (e.g., ClearML, MLflow) Ability to design scalable, high-performance ML systems (not just prototypes) Strong problem-solving ability and comfort operating independently in a fast-paced environment What Makes You a Great Fit High agency: you ship, iterate, and fix what’s broken—without waiting for permission You’ve delivered ML systems end-to-end in production (data → model → deployment → iteration) You’re a strong engineer who cares about getting better—trajectory matters here You communicate clearly, especially with a remote and cross-cultural team You’re gritty and genuinely enjoy solving hard problems Bonus Points Experience building systems for document reading / understanding Ambitious, driven, and opinionated about quality and craft Experience with deep learning inference frameworks (e.g., TensorRT, PyTorch compile) and optimizing inference performance You keep up with current ML/AI developments and can apply them pragmatically What We Offer Competitive salary + meaningful equity Comprehensive benefits (health, dental, vision) Professional development budget (courses, conferences, research exploration) Real-world ML problems with direct impact High growth potential