About Boon

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 is backed by leading Silicon Valley venture capitalists.

Our AI agents embed directly into existing workflows, from preconstruction estimating to bid management. They automate the repetitive tasks that drain time and margins while surfacing the insights leaders need to make faster and more confident decisions.

The result is measurable impact. Teams move faster, bids are submitted sooner, win rates increase, and costs are reduced. Boon enables construction companies to build more, generate more revenue, and grow with confidence.

About the Role

Boon AI is building the agentic operating system for construction preconstruction — the layer that reads blueprints, specs, and bid documents, and does the estimator's work with them. Our platform spans a Rails product monolith, Python computer-vision services (DINOv3/SAM-class vision models reading drawings), an LLM agent runtime orchestrating multi-step construction workflows, and model/eval infrastructure that keeps accuracy honest. We're live with GCs and subs across the country, shipping daily, and scaling from thousands to hundreds of thousands of drawings per month.

As a Senior Software Engineer, you'll own meaningful features and services across this platform, solve challenging technical problems, and help build a system that scales with our customers.

In this role, you will

Own features and services end to end across the Rails product app, Python ML/CV services, agent SDK layer, and data platform — balancing customer requirements, maintainability, and shipping speed

Improve the scalability, reliability, and cost efficiency of our computer vision/LLM/VLM inference pipelines as we scale blueprint throughput

Build and improve our model infrastructure, including vision model integration, LLM orchestration, agent workflows, MLflow registry, and eval harnesses

Contribute to architectural decisions, write clear design docs, and raise the engineering bar through thoughtful code review

Share knowledge and mentor teammates as the engineering team grows

Partner with product and engineering teammates to scope work, evaluate build-vs.-buy decisions, and turn customer needs into reliable software

Write and ship production code regularly, troubleshoot issues, and participate in incident response

You’re a Great Fit If

You've shipped production systems that handle messy real-world input — documents, PDFs, images, OCR, or user-generated data

You have sound engineering judgment about when to add complexity, when to keep things simple, and when to use proven open-source or paid solutions

You've built or operated computer vision or LLM/agent systems in production, or have strong adjacent experience and want to work deeply in this space

You care about testing and evals as practical tools for improving accuracy and reliability

You move fast while keeping the foundations strong, and can recognize when a part of the system needs investment

You thrive in flat, direct, high-velocity teams where technical decisions are grounded in code, data, and customer needs

Bonus: construction, AEC, or other vertical-SaaS experience; or experience helping a product scale at a growing startup

Culturally, you embody working as “one team” and strive to “get things done,” taking ownership and helping teammates move work forward

Requirements for the Role

3+ years of experience building production software, with a track record of delivering in fast-paced environments

Strong experience in at least one of: Rails or Python applications, production computer vision pipelines, LLM/agent systems, or data-intensive B2B SaaS

Hands-on experience with cloud infrastructure (AWS and/or GCP), PostgreSQL, background job or messaging systems (such as Sidekiq or RabbitMQ), and modern deployment practices

Experience owning features or services from technical design through deployment and ongoing operation