Investigations Data Scientist, Deceptive Behaviors - USDS

is built to help imaginations thrive. This is doubly true of the teams that make TikTok possible.
Together, we inspire creativity and bring joy - a mission we all believe in and aim towards achieving every day.
To us, every challenge, no matter how difficult, is an opportunity; to learn, to innovate, and to grow as one team. Status quo? Never. Courage? Always.
At TikTok, we create together and grow together. That's how we drive impact - for ourselves, our company, and the communities we serve.
Join us.

Team Intro
We are seeking an experienced Investigations Data Scientist to join the Trust and Safety organization within USDS. You will use your investigative and adversarial mindset to help us identify, detect, and mitigate Deceptive Behavior (DB) networks operating on TikTok. You will support a team of cross-functional subject matter experts to data mine threat actor abuse tactics, develop predictive models, and conduct comprehensive proactive and reactive investigations using analytical skills, subject-matter expertise, and regional experience.
The Investigations Data Scientist will have the responsibility to perform social network analysis at scale to discover, identify, and mitigate the most harmful threats targeting the platform. You will closely collaborate with engineers and behavioral scientists to resolve complex threats that reach across topic or feature areas and will require network analysis and the creation of detection pipelines. You will develop actionable recommendations, and continually iterate solutions to scale your impact. The work of the Intelligence & Integrity team is critical to TikTok user safety, and the Investigations Data Scientist will have the opportunity to identify and mitigate the most harmful threats targeting the platform and our users.

Our Investigations Data Scientist performs a critical function that supports our efforts to address objectionable or disturbing content. Content that the Intelligence & Integrity team interacts with includes images, video, and text related to every-day life, but it can also include (but is not limited to) bullying; hate speech; child abuse; sexual assault; torture; bestiality; self-harm; suicide; and murder.

It is possible that this role will be exposed to harmful content on a daily basis.

In order to enhance collaboration and cross-functional partnerships, among other things, at this time, our organization follows a hybrid work schedule that requires employees to work in the office 3 days a week, or as directed by their manager/department. We regularly review our hybrid work model, and the specific requirements may change at any time.

Responsibilities

• Investigate and document coordinated deceptive behavior of threat actors, data mine behaviors and tactics to perform threat actor profiling, develop models to extract scalable and explainable signals of deceptive behaviors, and work with cross-functional stakeholders to mitigate and disrupt complex adversarial networks.
• Use all available internal and external data sources to produce actionable intelligence on high-harm threat actors, their networks, and threat organizations in the topic area of Influence Operations.
• Apply structured analytic techniques, data science, and intelligence tradecraft to perform social network analysis of large attribute, ideational, and relational data sets to identify threat actor networks, critical nodes, and kill-chains.
• Work cross-functionally with product managers, program managers, security, operations, policy, and communications teams to address gaps in current threat response processes such as detection and mitigation.
• Collaborate with a team of global experts that respond to known threat actors and proactively build and tailor queries to discover and identify potential threats.

Qualifications

Minimum Qualifications

• Bachelor's degree or higher in Computer Science, Data Science, Computational Social Science, Data Journalism, Cybersecurity, Engineering, Economics, other relevant fields, or equivalent experience.
• 3 years of experience conducting data-driven social network analysis for social media organizations, law enforcement, and/or intelligence community agencies.
• Experience should include discovering and correlating high-harm threat actors, networks, and organizations across global markets by performing mixed-methods quantitative and qualitative analysis of large data sets including attribute, ideational, and relational data.
• Advanced proficiency understanding of statistical analysis.
• Advanced proficiency in SQL or other relational database languages.
• Intermediate proficiency in a functional or object oriented programming language (e.g. Python, R).
• Understanding of Social Network Analysis, Machine Learning Algorithms, Deep Learning, or Recommendation Systems

Preferred Qualifications

• An understanding of online deceptive and manipulative behavior. Knowledge of the signals of specific threat actors, their cross-platform tactics, and how they evolve or change over time.
• Independently troubleshoot technical issues or bugs
• Rapidly shift priorities based on evolving challenges to the platform
• Identify anomalous behavior and determine ways for further exploring new research leads
• Communicate complex concepts to broader stakeholders without shared expertise
• 2 years of experience leading projects and managing stakeholder relationships.
• Project management skills to ensure impactful output, achieve stakeholder alignment, and manage competing priorities.
• Experience with data modeling and statistical analysis techniques, including: hypothesis testing, model evaluation, and common regression/classification algorithms.
• Your ability to work in a high tempo environment, adapt, respond to day-to-day challenges of the role.
• Your resilience and commitment to self-care to manage the emotional demands of the role.

Wellbeing Statement
Trust & Safety recognizes that keeping our platform safe for TikTok communities is no ordinary job. It can be rewarding, psychologically demanding, and emotionally taxing. This is why we are sharing the potential hazards, risks and implications in this unique line of work from the start: so our candidates are well informed before proceeding.

We are committed to the wellbeing of all our employees and promise to provide comprehensive and evidence-based programs, to promote and support physical and mental wellbeing throughout each employee's journey with us. We believe that wellbeing is a relationship and that everyone has a part to play, so we work in collaboration and consultation with our employees and across our functions in order to ensure a truly person-centred, innovative and integrated approach.

D&I Statement
TikTok is committed to creating an inclusive space where employees are valued for their skills, experiences, and unique perspectives. Our platform connects people from across the globe and so does our workplace. At TikTok, our mission is to inspire creativity and bring joy. To achieve that goal, we are committed to celebrating our diverse voices and to creating an environment that reflects the many communities we reach. We are passionate about this and hope you are too.

Accommodation Statement
TikTok is committed to providing reasonable accommodations in our recruitment processes for candidates with disabilities, pregnancy, sincerely held religious beliefs or other reasons protected by applicable laws. If you need assistance or a reasonable accommodation, please reach out to us at https://shorturl.at/ktJP6

Data Security Statement
This role requires the ability to work with and support systems designed to protect sensitive data and information. As such, this role will be subject to strict national security-related screening.