Computer Vision, Applied Research Scientist

About the Company

Boon is the professional AI platform built specifically for construction. Founded in the San Francisco Bay Area in 2023 by product and engineering leaders from Samsara, Apple, Google and DoorDash, Boon builds AI agents that automate repetitive tasks in construction workflows.

Responsibilities

• Design and evaluate novel multi-stage vision architectures for construction drawing understanding
• Drive architecture decisions including backbones, decoders, and fusion strategies
• Take models from experimental notebooks to the production inference pipeline
• Collaborate with ML engineers on deployment, quantization, and serving
• Define evaluation datasets and metrics to track model progress

Requirements

• 3-7+ years in computer vision research
• Hands-on expertise in multi-modal dense prediction (segmentation, detection, or joint vision-language tasks)
• Production experience with modern vision transformer backbones (SAM, DINOv2/v3, CLIP, SigLIP, or similar)

Preferred Qualifications

• Experience with Graph Neural Networks or relational reasoning architectures
• Experience with text spotting, OCR, or scene text detection
• Experience with self-supervised pretraining (MAE, DINO, or similar)
• Published papers at top venues (CVPR, ICCV, ECCV, NeurIPS, ICLR)

Benefits

• Direct ownership of research on a novel foundation model
• Autonomy to propose and run your own experiments
• Support for publishing work at top research venues