Machine Learning Engineer: Evaluation

Bedrock Robotics
San Francisco, California, United StatesFull-timePosted Aug 25, 2026

About the role

Join the team bringing advanced autonomy to the built world

At Bedrock, we're moving AI out of the lab and into the real world. Our team includes veterans who helped launch Waymo, scaled Segment to a $3.2B acquisition, and grew Uber Freight to $5B in revenue. Today, we're deploying autonomous systems on heavy construction equipment across the country, improving safety on job sites and accelerating schedules on critical infrastructure projects.

We're not here debating the future of AI. We're deploying it in the real world. In just two years, we've raised $350M and achieved the first fully autonomous excavator deployments in construction.

This is where algorithms meet steel-toed boots. You'll work alongside construction veterans and world-class engineers to solve physical-world problems that simulations can't touch. If you're ready to do meaningful work on hard problems, we'd love to have you join us.

Machine Learning Engineer: Evaluation

Bedrock is bringing autonomy to the construction industry! We’re a group of veterans from the autonomous vehicle industry who are passionate about bringing the benefits of automation to areas in the construction industry currently underserved by the market.

We’re looking for a highly motivated engineer with experience evaluating complex ML systems deployed in the real world. Your Mission: Translate the infinite nuance of the built world into actionable, AI-native evaluations that accelerate Bedrock Operator adoption.

The ideal candidate has hands-on experience in building evaluation systems and designing and executing statistical tests to gauge performance deltas between system iterations. More importantly, you’ve iterated on complex ML systems run in production environments, and you understand the complexities that come with it.

What You’ll Do

Design and maintain eval systems:

Build pipelines for measuring system performance – across open loop and closed loop simulation, hardware in the loop systems, and field data from Bedrock Operator equipped machinery. Excite other teams to gain insights earlier in the development cycle through streamlined workflows.

Develop Metrics

Connect product goals and system behavior - by bridging real-world specification to measurable indicators from logged data. Empower confident decision making from parameter tuning to program planning by slicing through the noise and delivering objective insights.

Classify Data Sources For Training And Testing

Implement infrastructure and classifiers - to self-annotate data and allow creation of datasets for a variety of training and evaluation use cases. Leverage models to source rich annotations for massive datasets to accelerate model iteration.

Predict System Performance

Model metrics and interpret results - from various sources ranging from raw sensor data to key leading indicators. Determine whether new construction sites pose hidden challenges and drive business decisions about deployment readiness.

What We’re Looking For

Engineers who are currently Senior or Staff level 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 and a data warehouse query language and comfort with development on infrastructure within parallelized cloud-based frameworks

Strong statistical analysis skills (e.g. classification, model fit bias determination, hypothesis testing, and uncertainty quantification)

Experience working with large datasets

Bonus points: We’re especially interested in engineers who have applied statistical backgrounds to ML research or real-world robotics applications.

Our roles are often flexible. If you don't fit all the criteria, or are in another location (especially one where we have an office like SF or NY), please apply anyway! We'd love to consider you.

Bedrock Robotics is an Equal Opportunity Employer

We’re committed to building a diverse and inclusive workplace. We consider all qualified applicants for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, ancestry, age, disability, veteran status, genetic information, or any other protected characteristic.

Reasonable Accommodations

We want our hiring process to be accessible to everyone. If you need an accommodation to participate in the application or interview process, please let your recruiter know so we can support you.

Responsibilities

  • Design and maintain evaluation systems
  • Develop metrics to connect product goals and system behavior
  • Classify data sources for training and testing
  • Predict system performance from various data sources

Qualifications

  • 5+ years of professional software engineering, data science, or research experience
  • 2+ years of experience analyzing modern ML or robotics system performance
  • Proficiency in Python and data warehouse query languages
  • Strong statistical analysis skills
  • Experience working with large datasets

Skills mentioned

PythonSQLMachine LearningModel EvaluationStatistical AnalysisStatistical ModelingData AnalysisData EngineeringData PipelinesCloud Computing

About Bedrock Robotics

Bedrock Robotics brings advanced autonomy to the built world, helping the construction industry build at the pace today's society demands. Our technology upgrades existing heavy equipment, enabling truly autonomous operation with expert level quality and superhuman safety. At a time when we need to build faster than ever—from housing to data centers to factories and energy infrastructure—autonomous construction isn't just an innovation, it's an economic necessity.

Robotics Engineering51-200 employeesSan Francisco, California