Technical Architect

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 a 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. The Technical Architect sits across every one of those surfaces and makes sure the system we're building this quarter is the system we can still build on three years from now.

In this role, you will:

Own the end-to-end technical architecture across the Rails product app, Python ML/CV services, agent SDK layer, and data platform — including the hard tradeoffs between enterprise customer requirements and shipping speed

• Drive scalability, reliability, and cost architecture of our computer vision/LLM/VLM inference pipelines as we scale blueprint throughput by 100×
• Set the technical direction for our model infrastructure — vision models, LLM orchestration, agent runtime, MLflow registry, eval harnesses, and GPU budget
• Lead architectural review, raise the engineering bar through code review and design docs, and mentor senior engineers on cross-system tradeoffs
• Partner with the CEO and product on the 12–18 month technical roadmap: what we build in-house, what we buy, what we deprecate, and when to invest in platform vs. features
• Still write code — this is a working architect role; you'll be in incident response, PR review, and the hardest technical problems on a weekly basis

You’re a Great Fit If:

• You've shipped production systems that handle messy real-world input — documents, PDFs, images, OCR, user-generated chaos — not just clean API-to-API services
• You have strong opinions on monolith vs. services, model-in-the-loop UX, when to add complexity, and when "just add another microservice" is the wrong answer
• You've built or deeply operated computer vision or LLM/agent systems in production, and you understand eval infrastructure as a first-class engineering discipline

You move fast without breaking the foundations — comfortable shipping daily, comfortable saying "stop, we need to rebuild this part" and similarly “stop, we should NOT reinvent the wheel and use battle-tested open-source/paid solutions”

• You thrive in flat, direct, high-velocity teams where the architect sets the technical path and defends it with code and data, not slides
• Bonus: construction, AEC, or other vertical-SaaS experience; or you've taken a company from Series A to C technically
• Culturally, you embody working as “one team” and strive to “get things done”, instead of passing the buck around

Requirements for the role:

• 10+ years building production software; 3+ years as senior staff, principal, architect, or CTO at a product company
• Deep experience with at least two of: large Rails or Python monoliths, computer vision pipelines in production, LLM / agent systems at scale, data-intensive B2B SaaS
• Hands-on fluency with cloud infrastructure (AWS and/or GCP), PostgreSQL at scale, background job systems (RabbitMQ, SideKiq), and modern deployment practices
• Track record of leading architectural decisions that held up under 10×+ growth
• Has written and shipped production code in the last 6 months — and plans to keep doing so
• Familiar with some SRE (Service Reliability) and DevOps - Kubernetes, Helm, CI/CD and ability to drive and collaborate with Boon’s dedicated SRE teammates.