Ground-Truth Analyst

Munich, Germany /
Engineering /
Cape Analytics provides instant property intelligence for buildings across the United States. Cape Analytics enables insurers and other property stakeholders to access valuable property attributes at time of underwriting, with the accuracy and detail that traditionally required an on-site inspection, but with the speed and coverage of property record pre-fill. Founded in 2014, Cape Analytics is backed by leading venture firms and innovative insurers and is comprised of computer vision, data science, and risk analysis experts.

Position Summary:
At the heart of our highly scalable, state-of-the-art machine learning models lies large amounts of human-annotated data (ground truth) used for training and testing our models. Accurate data is crucial for our models to perform well. Scalability is another important aspect, which is why we outsource most of the ground truth generation to our contractors. We are looking for an experienced Data Analyst who will own and manage the ground truth generation pipeline end-to-end. S/he will be the contact person for everything ground truth related, from training our contractors on new taxonomies to quantifying the data accuracy and developing new methods to improve it. Strong communication skills, scientific approach, strong foundation in statistics, data analysis and data management will be critical to success. S/he must be at ease working in an agile environment with full ownership and little supervision. This person should embody a passion for continuous improvement, automation and data quality.

What You'll Do:

    • Take mental ownership of our ground truth pipeline and help us extend its functionality to support the development of innovative new products. Coordinate with multiple teams at Cape to meet short-term and long-term objectives.
    • Design and implement methods to quantify and improve ground truth data accuracy in collaboration with the data scientists.
    • Design and experiment new ways for more accurate and efficient ground truth generation.
    • Participate in creating and updating taxonomies for machine learning models. Create documentation for taxonomies and train the ground truth contractors.
    • Evaluate ground truth contractors and provide them feedback to keep high quality standards.
    • Leverage the feedback from the contractors to improve the taxonomy definitions, and collaborate with the engineering team to improve the tools for data collection and management.
    • Triage and report bugs throughout our data pipeline.
    • Take ownership of communicating changes to the appropriate end-users.
    • Maintain comprehensive documentation of data, definitions, tables, and schemas across multiple systems.
    • Build and support visualization and exploration capabilities around our data sets.
    • Contribute to constantly improving data quality/quality assurance best practices. 


    • BS (MS is preferred) in Statistics, Analytics, Computer Science or related STEM fields.
    • Excellent critical thinking, troubleshooting and analytical problem-solving abilities.
    • Excellent verbal and written communication skills. Must be able to create clear documentations, communicate with off-shore contractors and with multiple teams at Cape.
    • Solid foundation in Statistics and Data Analysis.
    • Coding Skills: Python, SQL.
This role will be located in the MUC office and working remotely is not an option.

We believe:

*Talent is critical, but best when tempered with humility
*Self-motivation leads to the best outcomes
*Open, direct communication is a sign of respect
*Teamwork drives success
*Having fun together is an important part of the job

***Cape Analytics is an E-verify participant.***