SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Socure is building identity trust infrastructure for the digital economy, verifying identities in real time and stopping fraud before it starts. RiskOS is Socure's AI-powered orchestration and decisioning platform providing a centralized control plane for identity, fraud, and risk workflows. Workforce Verification is a key RiskOS vertical focused on stopping workforce identity fraud—fake applicants, deepfake interviews, identity rental, and ghost employees.
As a Data Scientist II for Workforce Verification on the RiskOS team, you will own the end-to-end data science lifecycle for a critical new product area focused on workforce identity and hiring fraud. You will explore and analyze rich, multi-source data (identity, device, behavioral, resume and application signals) to uncover fraud patterns in the hiring funnel, then translate those insights into rules, conditions, and machine learning models deployed within RiskOS workflows.
This role sits at the intersection of fraud analytics, natural language processing, and Generative AI. You will help design and evaluate GenAI-powered components such as resume verification agents and explanation tools that operate on unstructured, text-heavy data like resumes, job descriptions, and interview artifacts.
Key responsibilities include: owning the full data science lifecycle for Workforce Verification use cases—from data exploration and hypothesis generation through model development, evaluation, deployment, and monitoring; exploring workforce-related data sources (applications, resumes, device and behavioral telemetry, background checks, ATS/HRIS integrations) to identify patterns of workforce fraud; designing and implementing rules, conditions, and heuristic logic in RiskOS workflows to detect high-risk workforce events; developing and evaluating machine learning models for workforce risk and identity assessment; collaborating with product teams on GenAI-powered features and building evaluation datasets; partnering with engineering to productionize models and components; translating model performance into customer-facing narratives; incorporating customer feedback to continuously improve logic and models; and operating with a product mindset and strong ownership.
The role is hands-on but embedded in the RiskOS Data Science team with guidance from senior data scientists and close partnership with product, engineering, and Workforce GTM. It is ideal for a data scientist with strong fraud or risk experience who wants broader end-to-end ownership, enjoys working with unstructured text, and is comfortable rolling up their sleeves on data engineering and productionization when needed.
REQUIREMENTS:
- Bachelor's or Master's degree in Computer Science, Statistics, Mathematics, Engineering, or a related quantitative field, or equivalent practical experience
- 3–6 years of hands-on experience in data science, machine learning, or applied analytics, with meaningful work on fraud, risk, trust & safety, or workforce/hiring analytics preferred
- Experience owning end-to-end analytics and/or model development projects: problem framing, data wrangling, feature engineering, model training, evaluation, and deployment support
- Strong proficiency in Python and SQL, including experience with common data science and ML libraries (pandas, scikit-learn, XGBoost, PySpark, or similar)
- Comfort working with large, messy, and heterogeneous datasets (JSON workflows, logs, event streams, third-party enrichments) and building reusable abstractions
- Exposure to Natural Language Processing and/or unstructured text analytics—such as resume or document parsing, entity extraction, similarity search, or embedding-based methods—ideally applied in real-world products
- Some hands-on experience working with Generative AI or LLM-based products (commercial LLM APIs, prompt design, RAG-style retrieval, or evaluation of LLM outputs), with an interest in deepening this skill set
- Strong analytical and problem-solving skills, including comfort 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 (ETL transforms, Airflow/Spark jobs, basic monitoring) in partnership with engineering
- Clear, concise communication skills and ability to explain complex analyses, models, and GenAI behavior to non-technical stakeholders
- Bias toward ownership, learning, and collaboration—comfortable in fast-paced, evolving environments
Nice to have: Direct experience with workforce, HR tech, ATS/HRIS data, or hiring funnel analytics; prior work on identity verification, device intelligence, or orchestration/rules engines; familiarity with evaluation and monitoring of GenAI systems.
