Linguistic Data Manager

Location: Gothenburg, Sweden or Remote

We are looking for an outstanding linguistic data manager to help us leverage text and NLP modeling techniques to find threat patterns and signals in vast amounts of texts. This position requires an organized person who has extensive experience in creating high quality datasets for training text based machine learning models, and solid knowledge in using linguistic and statistical methods in order to align datasets to models and use cases. You should have programming experience in python and feel comfortable in a technical environment. 

This role is part of the Analytics team in the R&D Organization.  You will work in a highly effective and collaborative team dedicated to building an NLP system which understands threat-signals from text as well as a human analyst.

You would get the chance to develop great software in a fast-moving environment close to our global clients and their needs. Together, we’ll improve our product to meet increasing demands while focusing on scalability and quality. You will also get a chance to experiment with new technology and explore what solutions are most suitable for solving real-world problems. You would join a dynamic team eager to take on new challenges and are passionate about what they do.

Your responsibilities will include:

• Machine Learning:
• Ownership of our text based machine learning models
• Developing machine learning models
• Understanding the impact of models in our product

• Manage Sources & Data:
• Creating training datasets of the highest quality
• Understanding the lifecycle of our data sources
• Using linguistic and statistical tools for error analysis and dataset consistency
• Plan and coordinate the creation of tools for acquiring new training data
• Ownership of text training data sets and the relative documentation
• Lead Annotation Process 
• annotation guidelines
• Adjudication
• Continuous Monitoring
• Vendor Management
• Serve as  Linguistic Expert:
• Defining new linguistic resources needed to expand Recorded Future’s NLP products
• Locate existing linguistic open source or proprietary resources (datasets & text analysis tools)
• Together with product management define new events and entity categories
• Clarify linguistic requirements and dependencies to other teams
• Performing quality assessment of our current linguistic performance and resources

Requirements: 

• Bachelor degree in computational linguistics, machine learning, computer science or similar discipline.
• Experience in the data lifecycle process for NLP datasets.
• Comfortable in Python/Java/Scala 
• Experience in tooling for handling data and data analysis
• Experience with Spacy, Pytorch, git, elasticsearch, mongodb is a plus

Diversity has been essential to Recorded Future since day one, and that is clearly visible in all teams in the company, yet there’s always room for improvement. In essence, we welcome applications that will help us improve this even more.

#LI-Remote