Position Overview
Bobyard solves non-trivial CV problems in order to automate takeoffs for contractors. We can save them dozens of hours for each project easily. This requires a complex system of models that produce better than human results.
You will have very high autonomy in designing, executing, and iterating on products. We are a startup, and we move fast. You will be the world’s leading expert on the products you build. We look for world-class engineers who have both a vision for the product but also the ability to go heads down and produce exceptional code.
ResponsibilitiesDevelop and train CV models
Design end-to-end pipelines for data ingestion, training, evaluation, and inference
Improve model accuracy, robustness, and performance at scale
Work closely with fullstack and product to integrate models into production
Analyze real customer data to identify failure modes and opportunities
Stay current with relevant research and apply it pragmatically
Strong background in computer vision and deep learning
Experience shipping ML models into real production systems
Comfortable working with messy, real-world data
Research-minded but execution-focused
High ownership mindset — you don’t wait to be told what to fix
Fast learner who can navigate unfamiliar problem spaces
Passion for solving hard, real problems that matter to customers
This is a full-time & in-person role in the SF Bay Area. Learning rate and dedication are vital factors. If you can prove that you can execute on the products our customers are waiting for at the speed and quality the market demands (or if you can prove that you will acquire the ability to do so fast enough), we would love to work with you.
Top Skills
What We Do
Construction is one of the largest industries in the world, but it is also one of the least technologically innovative spaces. Conducting fast and accurate cost estimates is a massive pain point. Bobyard automates the construction takeoff process with CV and NLP models to make cost estimates 10x faster while eliminating mistakes.







