Machine Learning Engineer: Evaluation

About this role

Bedrock is seeking an experienced ML Engineer to design and maintain evaluation systems for autonomous construction machinery. You'll translate real-world performance data into actionable metrics and statistical insights that drive product decisions and accelerate adoption of autonomous systems in construction.

What you'll do

• Build evaluation pipelines measuring performance across simulation, hardware-in-the-loop, and field data from deployed machinery
• Develop and connect product goals to measurable performance metrics from logged sensor data
• Implement infrastructure and classifiers to self-annotate data for training and testing datasets
• Create statistical models to predict system performance and assess deployment readiness at new construction sites
• Design and execute statistical tests to measure performance differences between system iterations
• Streamline evaluation workflows to enable other teams to gain insights earlier in development

What they're looking for

• Python and data warehouse query languages
• Statistical analysis (hypothesis testing, classification, uncertainty quantification, bias determination)
• ML and robotics system performance analysis
• Cloud-based parallelized computing frameworks
• Large dataset handling and processing
• Simulation and field data analysis
• Metrics design and product analytics
• Data annotation and classification systems