Bedrock Robotics
Machine Learning Evaluation Engineer
Bedrock Robotics, San Francisco, California, United States, 94199
Machine Learning Evaluation Engineer – Bedrock Robotics
Bedrock is bringing autonomy to the construction industry, leveraging the expertise of veterans from the autonomous vehicle industry to deliver automation solutions to underserved sectors.
We’re looking for a highly motivated engineer with experience evaluating complex ML systems deployed in real‑world environments. Your mission is to translate the built world’s nuance into actionable, AI‑native evaluations that accelerate Bedrock Operator adoption.
Responsibilities
Design and maintain evaluation systems: build pipelines to measure performance across open‑loop and closed‑loop simulation, hardware‑in‑the‑loop setups, and field data from Bedrock Operator‑equipped machinery, enabling early insights for other teams.
Develop metrics: bridge real‑world specifications with measurable indicators from logged data to inform decisions from parameter tuning to program planning.
Classify data sources: implement infrastructure and classifiers for self‑annotation to create datasets for training and evaluation, leveraging models to source rich annotations.
Predict system performance: model metrics and interpret results from raw sensor data and key leading indicators, assessing new site challenges to guide deployment readiness.
Qualifications
Senior or Staff level engineers with 5+ years of professional software engineering, data science, or research experience.
2+ years of professional experience analyzing modern ML or robotics system performance on real‑world problems.
Proficiency in Python, a data‑warehouse query language, and comfort developing infrastructure within parallelized, cloud‑based frameworks.
Strong statistical analysis skills (classification, model‑fit bias determination, hypothesis testing, uncertainty quantification).
Experience working with large datasets.
Bonus: applied statistical backgrounds to ML research or real‑world robotics applications.
Our roles are often flexible. If you don’t meet every criterion or are located elsewhere (especially in cities with a Bedrock office such as SF or NY), please apply—we’d love to consider you.
Location: San Francisco, CA
About Bedrock Robotics We’ve assembled one of the industry’s most experienced autonomous technology teams, scaling breakthroughs across transportation, infrastructure, and enterprise software. Our leaders helped launch the first public self‑driving cars at Waymo, scaled systems for Segment’s $3.2 B acquisition, and grew Uber Freight to $5 B in revenue.
Our autonomous systems are already installed on heavy machines nationwide, learning on real construction sites to shape billion‑dollar infrastructure projects. In just over a year, we’ve raised $80 M, deployed our equipment, and partnered with forward‑thinking contractors to meet America’s growing demand for housing, data centers, and manufacturing while addressing the labor shortage.
Join a team where algorithms meet steel‑toed boots, collaborating with construction veterans and engineers to solve meaningful problems that directly impact physical world construction.
#J-18808-Ljbffr
We’re looking for a highly motivated engineer with experience evaluating complex ML systems deployed in real‑world environments. Your mission is to translate the built world’s nuance into actionable, AI‑native evaluations that accelerate Bedrock Operator adoption.
Responsibilities
Design and maintain evaluation systems: build pipelines to measure performance across open‑loop and closed‑loop simulation, hardware‑in‑the‑loop setups, and field data from Bedrock Operator‑equipped machinery, enabling early insights for other teams.
Develop metrics: bridge real‑world specifications with measurable indicators from logged data to inform decisions from parameter tuning to program planning.
Classify data sources: implement infrastructure and classifiers for self‑annotation to create datasets for training and evaluation, leveraging models to source rich annotations.
Predict system performance: model metrics and interpret results from raw sensor data and key leading indicators, assessing new site challenges to guide deployment readiness.
Qualifications
Senior or Staff level engineers with 5+ years of professional software engineering, data science, or research experience.
2+ years of professional experience analyzing modern ML or robotics system performance on real‑world problems.
Proficiency in Python, a data‑warehouse query language, and comfort developing infrastructure within parallelized, cloud‑based frameworks.
Strong statistical analysis skills (classification, model‑fit bias determination, hypothesis testing, uncertainty quantification).
Experience working with large datasets.
Bonus: applied statistical backgrounds to ML research or real‑world robotics applications.
Our roles are often flexible. If you don’t meet every criterion or are located elsewhere (especially in cities with a Bedrock office such as SF or NY), please apply—we’d love to consider you.
Location: San Francisco, CA
About Bedrock Robotics We’ve assembled one of the industry’s most experienced autonomous technology teams, scaling breakthroughs across transportation, infrastructure, and enterprise software. Our leaders helped launch the first public self‑driving cars at Waymo, scaled systems for Segment’s $3.2 B acquisition, and grew Uber Freight to $5 B in revenue.
Our autonomous systems are already installed on heavy machines nationwide, learning on real construction sites to shape billion‑dollar infrastructure projects. In just over a year, we’ve raised $80 M, deployed our equipment, and partnered with forward‑thinking contractors to meet America’s growing demand for housing, data centers, and manufacturing while addressing the labor shortage.
Join a team where algorithms meet steel‑toed boots, collaborating with construction veterans and engineers to solve meaningful problems that directly impact physical world construction.
#J-18808-Ljbffr