We are seeking a Data Scientist to join us in our mission to become an industry leader in the use of advanced modelling to safeguard the integrity of online content. We are looking for someone with experience of ML models to join a growing team responsible for building and deploying models to help us ensure our platform content continues to be of the highest possible quality. You will collaborate with departments across Trustpilot including Product, Commercial, Engineering and Legal to develop, deploy and maintain innovative models at scale that tackle some of the most interesting Data Science use cases within our business.
To succeed in this role you will have a strong technical background as a Data Scientist, an adaptable mindset, and good knowledge of the interface between data science and engineering. Prior knowledge of fraud detection methods and ML models to detect suspicious or unusual patterns in data is a requirement for this role. Experience of working in an interdisciplinary team is a big plus.
In your role
- You will be involved in some of our most exciting Data Science projects: ranging from scoring models to natural language processing to pattern recognition
- Along with other team members, you will develop and maintain the data science-driven models that we use to safeguard platform content integrity and proactively identify unusual behaviour
- You will deliver the Data Science component of key projects
- Using your existing knowledge of anomaly detection and behavioural analytics, you will identify opportunities to improve our coverage of fraud detection models
- You will use your analysis, modelling, text mining, and data engineering skills to help identify new opportunities to use data to safeguard online content integrity
- Working alongside ML Engineers, you will deploy production-ready ML models
- You’ll be joining a friendly, international, team of like-minded people in central Copenhagen
We are looking for
- Experience with analytical and quantitative problem solving using advanced statistical techniques, e.g. regression modelling, simulation, clustering, forecasting, Markov chains and queuing theory
- Prior knowledge of fraud detection methods and ML models to detect suspicious or unusual patterns in data
- Proven ability to deliver technical projects to a commercial organisation
- A minimum BA/BSc degree in Statistics, Mathematics, Physics, Computer Science or related quantitative degree
- Experience in building and deploying ML models at scale, and strong data engineering skills
- Ability in Python, R & SQL for data manipulation, modelling and scripting, and experience of delivering production-ready code.
- Experience of working with large datasets. Knowledge of the data generated by websites or in the eCommerce sector, behavioural analytics, and experience of working with data from commercial systems (e.g. Salesforce) is a big plus
- Knowledge of data pipelining (e.g. via Airflow) and prior experience of cloud-based ML model deployment
- Great communication skills - both with technical colleagues and with business stakeholders
- 2+ years of relevant technical experience in a Data Science role, preferably in the technology sector or in a technical consultancy. We are particularly interested in Data Scientists with experience of behavioural algorithms, e.g. from the financial sector
- "20% time" - be the most innovative you can be and work on anything you’d like!
- The opportunity to be a key part of an exciting international growth journey
- The opportunity to work with leading data engineering technologies including Google BigQuery, Airflow and AWS, and with leading Data Science tools and emerging technologies for model building and deployment
- Opportunities to learn from the best and develop your career in a friendly, international, workplace
- Regular hackathons