Data Scientist II, Client Analysis

Socure•New York, NY

7d•$150,000 - $185,000•Remote

About The Position

Socure is seeking a Data Scientist (DS-II) to join their Data Science, Client Analysis team, based remotely in the USA. This role involves leveraging experience in algorithm development and large-scale data analysis to create compelling data narratives. The Data Scientist will partner with the go-to-market team to drive revenue by demonstrating the value of Socure's products to potential and existing customers through in-depth analysis during the pre and post-sales cycle. This position is ideal for a Data Scientist who enjoys communicating data insights to both technical and non-technical audiences and is motivated by contributing to new business generation, with a generous incentive bonus opportunity in addition to a competitive base salary.

Requirements

Degree in a quantitative field, or equivalent work experience; advanced degree preferred.
2+ years of experience in data science, data analysis, or analytics engineering.
Extensive theoretical and practical understanding of state-of-the-art supervised and unsupervised machine learning methods.
Proficiency in writing clean, performant Python code.
2+ years of experience working with massive real-life datasets.
Experience querying relational databases with SQL.
Experience with cloud tools and technologies in AWS, Azure, Databricks, or GCP.
Ability to tell compelling stories with data (dashboarding, building interactive data stories, and actionable presentations).
Ability to explain complex algorithms (ML/AI models) and analyses to non-technical audiences.
Excellent verbal and written communication skills, comfortable delivering presentations with clear, complete messages.
Thrives in a remote startup work environment, with strong skills in setting clear goals and self-accountability.
Experience in identity verification and fraud prevention (strongly preferred).

Nice To Haves

Experience with Python ecosystem: PySpark, Pandas, NumPy, H2O, SHAP, Seaborn, Jupyter, and related data-science libraries.
Experience with SQL and data warehouses: SQL, Redshift, Snowflake, and S3.
Experience with data processing: Databricks, Apache Spark, Apache Arrow, and Amazon EMR.
Experience with data pipelines and automation: Airflow, batch processing, SFTP/PGP, webhook data, and automated daily/weekly reporting.
Experience with model evaluation and risk analytics: backtesting, train/holdout/OOT analysis, performance monitoring, threshold tuning, and model/rule QA.
Experience with visualization and storytelling: Tableau, Looker, dashboards, and interactive presentations.
Experience with ML/AI workflows: supervised and unsupervised learning, transformers, clustering, graph analytics, explainability, and LLM/agentic workflows.
Experience with engineering and analytical practices: Git-based version control, production-quality and reproducible analysis, automated data-quality and validation testing, API integrations, and working with structured data formats such as JSON.

Responsibilities

Analyze massive customer data sets, derive actionable insights, and explain model performance and how customers can optimize risk management policies.
Act as a Data Science advocate, thoroughly understanding Socure's solutions (products, models, algorithms) and customer risk challenges to educate and influence from a scientific standpoint.
Create compelling data stories to illustrate how Socure helps customers eliminate identity fraud, improve end-user experience, and holistically support their risk management efforts.
Provide thought leadership and represent the customer's perspective in the development of Socure's next-generation core models and products.
Develop tools and automated workflows to enhance the speed, accuracy, and reproducibility of analyses.
Collaborate closely with Go-To-Market (GTM) teams (Sales, Solution Consultants, Account Managers, Technical Account Managers) to devise creative analytical approaches and identify opportunities for upsell and product enhancement.
Build ML models when exploring alternative approaches to established production models is beneficial.