At Signifyd we’re creating a new market. We’re constantly improving and expanding the technology that has changed what fraud protection for e-commerce looks like. So we don’t have time for office politics. We understand that different people have different work styles and we thrive on variety while learning from each other. We’re all Signifyers, so we know that what needs to get done will get done.
Signifyd is a place where no one is going to tell you how to do your job. If you want help, you'll get it — from all quarters. But we pretty much figure out what needs to be done, who's in the best position to do it and then let that person roll-up her or his sleeves and have at it. We're protecting retailers from online fraud in a way that's never been done before and we could use your help if you're someone:
- Who believes challenges are best overcome by thinking differently.
- Who knows his or her role, but isn’t confined by it.
- Who’s greatest satisfaction comes from helping customers succeed and achieve their dreams.
- Who isn’t afraid to disagree, convincingly, civilly and honestly.
- Who will stop and hold the door for a colleague, even if you’re running late.
Oh, and a few particulars for this role:
You will have the opportunity to apply your knowledge of machine learning, statistics and your analytical skills to develop models detecting fraud patterns. You will ideate, test and deploy advanced predictive signals to improve fraud detection performance. You will collaborate with other data scientists and engineers to build data pipelines, do feature prototyping, and write production-grade code to implement analytical algorithms and flexible strategies.
Specific job duties may include:
- Writing or modifying data pipelines to process and mine historical data
- Processing and analyzing data collected with research prototypes
- Ideation, prototyping, measuring predictive features transforming data into actionable information
- Prototyping and validating models and algorithms to boost model performance
- Writing production code (python, SQL, etc.) to deliver analytics content
Required Skills and Experience:
- An advanced degree (M.S. or Ph.D) in computer science, applied mathematics, or a comparable analytical field from an accredited institution
- Expert proficiency with an advanced data analysis toolkit (such as python/matplotlib, R, ROOT, etc.)
- Superior SQL skills with proven experience in relational databases and data warehouses
- 5+ years of demonstrated fluency with python and at least one other programming language
- 2+ yrs of experience with NoSQL databases and unstructured data
- 2+ yrs of experience setting up and using distributed/parallel processing frameworks such as Spark, Hadoop, Storm etc. is a big plus
- Demonstrated ability to develop high-quality code adhering to industry best practices (i.e., code review, unit tests, Gitflow)
- Possession of core analytics skills and expertise (as demonstrated by prior work):
- Knowledge of applied statistics and key concepts underlying statistical inference and inductive reasoning
- Experience designing experiments and collecting data
- Experience developing models based on sensor data, and an understanding of error propagation and the limitations of data subject to measurement uncertainties
- Demonstrable expertise in one or more areas: applied mathematics, predictive analytics, expert systems, ANNs/deep learning, graph theory, Markov Chain Monte Carlo, geo-informatics (GIS), language processing, risk analysis
- Work/project history reflective of a self-motivated professional who excels when given open-ended problems and broadly-defined goals, having an innate desire to discover the patterns and relationships in data that can be leveraged to provide business value