Computer Vision, Applied Research Scientist

About the role

We are building the first foundation model for construction drawings — a unified multi-modal vision system that reads, understands, and reasons about architectural, mechanical, electrical, plumbing, and structural plans the way a human estimator does. As a Computer Vision Applied Research Scientist at Boon, you will own end-to-end experiments on our foundation model, from architecture design through self-supervised pretraining, supervised fine-tuning, and shipping production models into our inference pipeline. This is a 80/20 research-to-production role.

What Success Looks Like

Within your first 12-18 months, the successful candidate will:

• Push our production model to ≥95% accuracy across multiple trades and scopes
• Design a genre-defining, novel architecture for construction drawing understanding
• Publish a paper on the work at a top venue (CVPR, ICCV, ECCV, NeurIPS, or ICLR).

What You Will Do

Research & Architecture Design and evaluate novel multi-stage vision architectures for construction drawing understanding — perception, text-object association, and relational reasoning across elements
Dive into architecture decisions: backbones, decoders, fusion strategies, loss functions, training regimes
Run rigorous experiments with clean baselines, ablations, and held-out evaluation on real construction drawings
Own supervised training and self-supervised pretraining strategies
Pursue research directions that compound accuracy across trades and scopes
Production Shipping
Take models from experimental notebooks to the production inference pipeline
Work hands-on with PyTorch, YOLO, SAM, DINO, and other modern CV stacks
Collaborate with ML engineers on deployment, quantization, and serving
Debug real failures on real customer drawings and close the loop into the next training run

Cross-Functional Work

Collaborate with the synthetic data, annotation, and infrastructure teams to make sure experiments have the data and compute they need
Partner with engineering leadership on the accuracy roadmap and strategic direction
Write clean internal research reports so the broader team can learn from your work
Present findings, trade-offs, and recommendations to engineering leadership

Data & Evaluation

Help shape what data we acquire and annotate, based on what the model actually needs
Define evaluation datasets and metrics that track progress honestly — not Kaggle-style leaderboard chasing
Identify failure modes on real customer drawings and design experiments that address them

You Are a Great Fit

• If you have 3-7+ years of computer vision research experience, ideally with a track record of published papers, open-source work, or production CV models
• If you have deep hands-on experience with multi-modal/vision transformers — segmentation, detection, or joint text+vision tasks
• If you have worked with modern vision transformer architectures like SAM, DINO, or similar foundation vision models
• If you can move from a research idea to a trained model to a production-shipped system with minimal hand-holding
• If you think about experiments rigorously — clean baselines, meaningful ablations, honest evaluation on real data
• If you have a point of view on architecture decisions and can defend it with reasoning and experimental evidence
• If you thrive on autonomy and set your own direction while staying aligned with team goals
• If you communicate clearly in English (written and verbal) and can collaborate during California business hours

Requirements

• 3-7+ years in computer vision research (industry research lab, applied science team, PhD research + industry, or equivalent)
• Strong track record of published CV research OR trained production CV models that shipped at scale
• 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)
• Strong PyTorch fluency and experience training large vision models
• Able to move models from research to production inference pipelines
• Strong fundamentals in deep learning: optimization, loss design, regularization, self-supervised learning
• Fluency in English (written and verbal)

Nice to Have

• Experience with Graph Neural Networks or relational reasoning architectures (most CV researchers do not — but it is a meaningful plus)
• Experience with text spotting, OCR, or scene text detection integrated with vision models
• Experience with LoRA, adapters, or parameter-efficient fine-tuning of large vision models
• Experience with self-supervised pretraining (MAE, DINO, or similar)
• Experience with engineering/technical drawings, document understanding, or layout analysis
• Contributions to open-source CV research
• Published papers at top venues (CVPR, ICCV, ECCV, NeurIPS, ICLR)