ML Engineer
About the role
Bucket Robotics is hiring a Machine Learning Engineer to advance CAD-native computer vision for manufacturing, turning 3D geometry and synthetic data into production-grade vision models deployed on factory floors.
Responsibilities
- Design, train, and evaluate computer vision and ML models for inspection and perception
- Develop novel approaches for learning from CAD, synthetic data, and limited real-world data
- Run rigorous experiments to understand model behavior, failure modes, and tradeoffs
- Improve model robustness across lighting, materials, viewpoints, and manufacturing variation
- Optimize models for edge deployment (latency, memory, reliability)
- Collaborate closely with engineering to integrate models into production systems
- Build evaluation frameworks and metrics that reflect real-world manufacturing requirements
- Stay current with cutting-edge research and proactively test promising ideas
Qualifications
- 3+ years experience developing ML systems in research or production environments
- Strong foundation in machine learning fundamentals and statistical reasoning
- Hands-on experience training deep learning models (e.g. PyTorch)
- Strong Python skills and comfort working in experimental codebases
- Enjoys deep problem-solving, experimentation, and analytical thinking
- Comfortable operating in ambiguity and iterating quickly
Skills
Benefits
- Competitive salary & meaningful equity – help define the core ML systems of the company
- Comprehensive benefits – health, dental, and vision insurance
- Professional development budget – conferences, courses, and research exploration
- A chance to work on hard problems – ML that has to work in the real world, not just benchmarks
About Bucket Robotics
Defect detection for manufacturing built from CAD and synthetic data.
Bucket Robotics is making defect detection faster, easier, and more deployable — starting with the 250M lbs of plastic wasted annually in U.S. manufacturing. Our platform turns CAD files into defect detectors. We generate synthetic, photorealistic training data to help factories catch flaws before they ship. No manual labeling, no real defects required. Our models deploy to edge hardware and integrate easily into existing automation stacks. We come from the self-driving world (Argo AI, Uber ATG, Stack AV), where we built reliable perception in high-noise, real-world environments. We're applying that experience to manufacturing: robust sensing, user-friendly interfaces, and fast iteration cycles. Manufacturers hesitate to adopt new sensing due to data concerns, integration risk, and poor UX. We’ve handled petabytes of regulated autonomy data — and built systems that earn trust. Legacy vendors like Keyence and FLIR offer hardware-centric tools with bloated pricing and outdated software. We’re building the opposite: flexible, modern tools that engineers want to use. Manufacturing is in the middle of a $700B automation wave across North America. Bucket Robotics is building the quality control infrastructure to match.
More open roles at Bucket Robotics
- Forward Deploy Engineer4mo agoHybrid (San Francisco, CA)
- Senior Full Stack Engineer5mo agoHybrid (San Francisco, CA) · Engineering