Senior Computer Vision Research Engineer

Bobyard; San Francisco (CA); On-site; USD 190,000 - 260,000; Full time

Job summary

Bobyard seeks a senior ML engineer to own end-to-end CV model pipelines for construction drawings in the SF Bay Area. You will design, implement, and iterate models that can detect, segment, OCR, and reason over complex drawings, driving production-ready solutions with minimal latency.

You will lead architectural decisions, translate construction trade requirements into model architectures, and mentor engineers to deliver robust, scalable systems achieving high-accuracy bids for customers.

Qualifications

• Shipping CV/ML models in production with real customer impact.
• Experience handling diverse construction drawing data.
• Proven leadership in end-to-end ML pipelines.

Responsibilities

• Build SOTA CV models for detection, segmentation, OCR and reasoning on drawings.
• Own data ingestion, labeling, training, evaluation and low-latency inference.
• Scale performance across 10,000+ drawing formats.
• Ship to production in collaboration with product and engineering.
• Identify failure modes in real customer data and fix quickly.
• Pragmatically apply research to ship next week with measurable impact.

Skills

Deep CV

Production ML

Model deployment

Leadership

Job description

Position Overview

Bobyard solves non‑trivial CV problems that move millions of dollars. Contractors burn dozens of hours per project doing takeoffs by hand. We automate it — with models that have to be better than human, on messy real‑world drawings.

You’ll have founder‑level autonomy to design, execute, and iterate. We move at startup speed — no research silos, no “publish and forget.” You’ll become the world’s leading expert on the models you ship. We want world‑class ML engineers with product taste and the ability to go heads down and produce exceptional systems.

Responsibilities

• Build SOTA CV models: Detect, segment, OCR, and reason over construction drawings. Accuracy isn’t academic — one mistake costs a customer millions.
• Own end‑to‑end pipelines: Data ingestion, labeling, training, eval, and low‑latency inference. If it doesn’t run in prod, it doesn’t count.
• Scale performance: Accuracy, robustness, latency. Our models face 10,000+ drawing formats and they need to just work.
• Ship to production: Work closely with fullstack and product to integrate models into features customers use daily. No throwaway notebooks.
• Attack failure modes: Dig into real customer data. Find where we break, why we break, and fix it fast.
• Apply research pragmatically: Stay current with the field. Take what works, ship it next week, measure impact.

Senior Level Scope

• Architectural Stewardship: Having shipped extensively at Bobyard, you define the infrastructure strategy, ensuring our ML systems remain scalable, modular, and performant across the increasing diversity of construction trades we support.
• Trade‑Expert Execution: You translate deep understanding of diverse construction trade requirements into model architectures. You don't just build models; you guide projects that require orchestration across multiple trades to solve complex, real‑world takeoff challenges.
• Technical Leadership & Mentorship: You elevate the team by embedding your learned expertise into our engineering culture, guiding junior engineers through the nuances of production‑grade CV and setting the bar for robust system design and testing.
• Strategic Project Ownership: You partner with Product and Engineering leadership to set the technical roadmap. You take ownership of high‑impact, cross‑functional projects, steering them from architectural ideation through to reliable production deployment.
• Final Arbiter of Quality: As a seasoned veteran of our model pipelines, you act as the ultimate decision‑maker on release readiness, enforcing standards that protect the integrity of the high‑stakes bids our customers rely on.

Desired Attributes

• Founder‑level drive: You own model performance like it’s your company. No one tells you what to fix — you already know.
• Deep CV + DL chops: You’ve trained models that actually shipped. Segmentation, detection, document AI, vision‑language — you’ve been in the trenches.
• Production killer: You’ve put ML into real products with real SLAs. You know the gap between 90% and 99.9% and how to close it.
• Messy data mindset: Real drawings are crooked, scanned, handwritten, and ugly. You love that. You turn noise into signal.
• Research‑minded, execution‑focused: You read papers, but you ship code. You bias to impact over elegance.
• Startup work ethic: This isn’t a research lab or a cushy big‑tech role. We’re at war with manual takeoffs in a $13T industry. You want that.
• Learning machine: New architecture on Monday, beating our baseline by Friday. You navigate unknown problem spaces fast.

This is full‑time & in‑person in the SF Bay Area. Learning rate and dedication beat pedigree. If you can prove you’ll ship models our customers trust with million‑dollar bids — at the speed and quality the market demands — we want you.

Comp Philosophy

We pay to win. Bobyard targets competitive top‑of‑market compensation because we hire people who ship and drive real impact — and we aim to reward that, including through variable pay tied to performance. Individual compensation is determined by role, experience, and contribution, at Bobyard's discretion.