Data Engineer

Boston, USA

Full Time
VideaHealth logo
Apply now Apply later

Posted 2 weeks ago

Summary: Join VideaHealth as key member of our Artificial Intelligence team on our mission to eventually improve dental health of millions of people. You will develop data pipelines and analyse and structure large data sets using proprietary AI algorithms.
About us: VideaHealth is a venture-backed startup developing artificial intelligence to automatically detect diseases in dental x-ray imaging. Spun out of MIT in 2018, our prior research has shown that dentists miss up to 50% of dental diseases. VideaHealth helps dentists detect these conditions and effectively communicate treatment recommendations to patients. Our product increases revenue for dentists and has the potential to reduce health risks for over 210 million patients every year in the US alone. In addition, we are helping dental insurance companies streamline their claims review process with AI. We have a strong core team and advisors, have raised over $6.5M in seed funding so far. Our investors include Pillar VC (invested in Path AI), Zetta Venture Partners (invested in Tractable), and angel investors like Frederic Kerrest (Co-founder of Okta), Avid Larizadeh Duggan (Former Google Ventures Partner), and Bradley Armstrong (Vice President at Slack). Our work has been featured at Techcrunch and the Wall Street Journal. We have great momentum and are now looking for ambitious talent to join our team! About the position: As a Data Engineer you will become a core member of Videa's Engineering team and execute on ambitious milestones, taking ownership of your own projects.
You will have a unique opportunity to be hands on and shape all stages of a complex data pipeline. This includes a large variety of tasks for which your analytical skills coupled with solid technical knowledge are a key requirement. This role will give you the opportunity to: * Apply and develop CV/NLP algorithms for the analysis of diverse datasets * Consolidate, normalize and inventory large and often unstructured medical datasets * Extract and retract information from medical datasets that range from images to text documents * Establish data-driven insights into patterns, correlations and opportunities based on health data * Work with external data partners to securely and efficiently transfer datasets
You will work closely with ML and Software engineers to analyse and structure large and diverse datasets using in-house, cutting-edge AI algorithms. We are looking for an individual with a strong analytical background who is not shy to take proactive responsibilities.
You will be able to contribute and grow your technical skills by building end to end highly impactful software medical devices that will ultimately impact the lives of millions of people. Your contributions will play a key role in building a great company from an early stage. We provide a competitive compensation package.


  • M.S. or equivalent in Maths, Statistics, Computer Science or related field.
  • Minimum of 2 years of hands-on experience as Data Scientist/Engineer performing statistical analyses and/or building out data pipelines
  • Strong software development skills including testing (Python)
  • Experience with data analysis / visualization libraries (pandas, matplotlib)
  • Proficiency with and experience with SQL, NoSQL
  • Strong communication and collaboration skills
  • Proactive, ambitious, and fast learner 


  • Experience with at least one deep learning framework (e.g. pytorch)
  • Knowledge of analyzing data using Hadoop/Spark
  • Familiarity with medical imaging data and file formats such as DICOM
  • Experience with De-identification of medical datasets
  • Familiarity with building tools to interactively visualize and analyze datasets
  • Experience with Flask, RestAPI, Docker
Job tags: AI Deep Learning Engineering Hadoop ML NLP NoSQL Pandas Python PyTorch Research Spark SQL