B

Boon

SaaS AI platform automating fleet workflows

Computer Vision Applied Research Scientist

Computer Vision +1Confirmed live in the last 24 hours
Full-timeRemote in USARemote

About the Job

Requirements

  • Have 3–7+ years of computer vision research experience in an industry research lab, applied science team, PhD research plus industry, or equivalent.
  • Have a strong track record of published computer vision research or trained production computer vision models that shipped at scale.
  • Have hands-on expertise in multimodal dense prediction, including segmentation, detection, or joint vision-language tasks.
  • Have production experience with modern vision transformer backbones such as SAM, DINOv2/v3, CLIP, SigLIP, or similar.
  • Have strong PyTorch fluency and experience training large vision models.
  • Be able to move models from research to production inference pipelines.
  • Have strong fundamentals in deep learning, including optimization, loss design, regularization, and self-supervised learning.
  • Be fluent in written and verbal English.
  • Be able to collaborate during California business hours.

Responsibilities

  • Design and evaluate novel multi-stage vision architectures for construction drawing understanding, including perception, text-object association, and relational reasoning across elements.
  • Drive architecture decisions involving backbones, decoders, fusion strategies, loss functions, and 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.
  • Take models from experimental notebooks to the production inference pipeline.
  • Work hands-on with PyTorch, YOLO, SAM, DINO, and other modern computer vision stacks.
  • Collaborate with machine learning engineers on deployment, quantization, and serving.
  • Debug failures on real customer drawings and incorporate findings into subsequent training runs.
  • Collaborate with the synthetic data, annotation, and infrastructure teams to ensure experiments have the required data and compute.
  • Partner with engineering leadership on the accuracy roadmap and strategic direction.
  • Write internal research reports so the broader team can learn from the work.
  • Present findings, trade-offs, and recommendations to engineering leadership.
  • Help shape what data the company acquires and annotates based on model needs.
  • Define evaluation datasets and metrics that track progress honestly.
  • Identify failure modes on real customer drawings and design experiments to address them.

Desired Qualifications

  • Experience with Graph Neural Networks or relational reasoning architectures.
  • Experience with text spotting, optical character recognition, 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 such as MAE or DINO.
  • Experience with engineering or technical drawings, document understanding, or layout analysis.
  • Contributions to open-source computer vision research.
  • Published papers at top venues such as CVPR, ICCV, ECCV, NeurIPS, or ICLR.
  • A track record of published papers, open-source work, or production computer vision models.

About the Company

Boon

SaaS AI platform automating fleet workflows

Boon is a SaaS platform for commercial fleets that automates workflows to boost profitability. It connects with existing systems like transportation management systems (TMS), electronic logging devices (ELDs), and payroll platforms, so fleets can adopt it with little disruption. The system uses large language models and transportation data to handle tasks such as data entry, document processing, and driver communications. It finds profitable loads, selects the best headhauls and backhauls, optimizes load choices, and provides real-time alerts. It also helps manage driver logs by spotting missing information and sending automated notifications, and it can recommend fuel stations to cut costs. Boon targets fleet operators and aims to double efficiency and profitability by reducing operating expenses and fully automating workflows.

Company size
51-200
Company stage
Series A
Total funding
$20.5M
Headquarters
San Mateo, CA
Founded
2023

Recently Posted Jobs

Explore more opportunities at Boon

See more jobs