Data Scientist ll - RiskOS

Socure’s RiskOS team is building practical protections for workforce identity and hiring fraud, with a focus on Workforce Verification. In this role, you’ll own the end-to-end data science lifecycle for workforce risk use cases, combining fraud analytics with NLP and Generative AI to deliver models, rules, and GenAI components that work inside RiskOS workflows.

Based in Seattle, WA (onsite), you will partner across RiskOS and Workforce product teams, engineering, and go-to-market stakeholders to turn model and rule performance into measurable outcomes for customers.

What you’ll do

• Own the full data science lifecycle for Workforce Verification use cases on RiskOS, from data exploration and hypothesis generation through development, evaluation, deployment, and ongoing monitoring.
• Explore workforce-related data sources including applications, resumes, device and behavioral telemetry, background checks, and ATS/HRIS integrations to identify fraud patterns such as fake resumes, identity rental, deepfake interviews, and injection attacks.
• Design, implement, and iterate on rules, conditions, and heuristic logic in RiskOS workflows to detect high-risk workforce events (for example repeated identities across multiple resumes, suspicious device patterns, and anomalous hiring flows).
• Develop and evaluate machine learning models for workforce risk and identity assessment, including scoring applicants for fraud risk, clustering related identities, and anomaly detection over hiring funnels. Apply Socure identity and device signals where appropriate.
• Collaborate with RiskOS and Workforce teams on GenAI-powered features such as the Resume Verification Agent and explanation agents, including defining inputs and outputs, building evaluation datasets, and setting quantitative and qualitative evaluation frameworks for LLM components.
• Work closely with engineering to productionize models, rulesets, and GenAI components in RiskOS by defining interfaces, supporting integration and testing, and contributing to monitoring, alerting, and feedback loops.
• Translate model and rule performance into customer-facing narratives with Product, Workforce GTM, and solution consulting, including examples like blocking fake applicants, reducing deepfake interviews, or preventing identity rental in hiring.
• Incorporate customer feedback and outcome data to improve Workforce Verification logic and models, including supporting experimentation and offline “test harness” design to evaluate new workflows and templates safely.
• Operate with a product mindset and strong ownership by documenting assumptions, decisions, and evaluation results, communicating trade-offs clearly, and surfacing risks, limitations, and opportunities.

What you bring

• Bachelor’s or Master’s degree in a quantitative field (Computer Science, Statistics, Mathematics, Engineering, or related) or equivalent practical experience.
• 3–6 years of hands-on experience in data science, machine learning, or applied analytics, with meaningful work in fraud, risk, trust & safety, or workforce/hiring analytics preferred.
• Experience owning end-to-end analytics and/or model development projects, including problem framing, data wrangling, feature engineering, model training, and evaluation and deployment support.
• Strong proficiency in Python and SQL, with experience using common ML and data science libraries such as pandas, scikit-learn, XGBoost, PySpark, or similar tools.
• Comfort working with large, messy, heterogeneous datasets (including JSON workflows, logs, event streams, and third-party enrichments) and building reusable abstractions or utilities.
• Exposure to Natural Language Processing and/or unstructured text analytics such as resume or document parsing, entity extraction, similarity search, or basic embedding-based methods in real-world products.
• Some hands-on experience with Generative AI or LLM-based products, such as commercial LLM APIs, prompt design, RAG-style retrieval, or evaluation of LLM outputs, with interest in deepening this skill set.
• Strong analytical and problem-solving skills, including reasoning about ambiguous signals and adversarial behavior in fraud or workforce contexts.
• Ability and willingness to take on light data engineering and production-oriented tasks when needed (for example ETL transforms, contributing to Airflow/Spark jobs, or instrumenting basic monitoring) in partnership with engineering.
• Clear, concise communication skills for explaining complex analyses, models, and GenAI behavior to non-technical stakeholders.
• A bias toward ownership, learning, and collaboration, comfortable working in a fast-paced environment with guidance from senior data scientists while expanding autonomy.

Technologies you’ll use

• Python, SQL, pandas, scikit-learn, XGBoost, PySpark
• Natural Language Processing, Generative AI, LLM-based products
• Commercial LLM APIs, RAG-style retrieval
• Airflow, Spark, ETL, JSON

Compensation

USD 140,000 - 170,000 per year