*About you *

Detailed-oriented, and interested in figuring out the ins-and-outs of a data format, for example how it's possible to cross-check where someone is born from their social security number.
You’re a data-wrangler, using big data to discover patterns and determine improvements
Awareness and expert of at least one form of data matching techniques, from regular expressions, through machine-learnt models, to natural language processing
You understand the difference between precision, recall, and F1, why they are important, and how to optimize for them.
You stay abreast of the latest technologies and share what you learn with others
You are not afraid of failing while experimenting with different technologies, development methodologies, and tools
You are fascinated by other cultures and interested building strong relationships with team members across the globe

What you’ll do

Work closely with the product team to identify data-class priorities
Build, modify, maintain, and improve data class definitions
Feed back technical needs and ideas to the engineering team that make data scanning more accurate and performant
Benchmark data scanning and matching, measuring accuracy against test data and telemetry from Open Raven scanning at scale
Document and report out current status, while investigating, advocating, and owning improvements
Break down larger data quality initiatives into pieces that deliver incremental business value and lead the team to execute on them
Drive quality mindset thoughts engineering practices

*What we’re looking for *

5+ years professional experience as a Software Engineer, Data Scientist, or Machine Learning Engineer
Experience working with large scale data
Prior success working on data processing and matching systems such as IDS, DLP, XDR
Ability to script and code in Python and/or Java
Excellent teamwork and communication
Ability to challenge the norm and maturity to advocate for changes for the greater benefit of the business
BS/MS/PhD CS or equivalent