Data Science Lead

About Prove

As the world moves to a mobile-first economy, businesses need to modernize how they acquire, engage with and enable consumers. Prove’s phone-centric identity tokenization and passive cryptographic authentication solutions reduce friction, enhance security and privacy across all digital channels, and accelerate revenues while reducing operating expenses and fraud losses. Over 1,000 enterprise customers use Prove’s platform to process 20 billion customer requests annually across industries, including banking, lending, healthcare, gaming, crypto, e-commerce, marketplaces, and payments. For the latest updates from Prove, follow us on LinkedIn.

Prove is driving the future of digital identity. We are looking for Provers who know how to make an impact. We’re talking self-starting professionals who thrive in a fast-paced environment, process information quickly, and make intelligent decisions. The work is challenging and requires not only smart but natural curiosity and tenacity. Teamwork is also important to us – we work together and play together.

Prove has big plans, and we’re excited about the future. If this sounds like the place for you – come join our team!

Title: Data Science Lead

Department: Business Operations

Reports To: Director, Data Science

FLSA Status: Exempt

Location: US Remote

This role is not eligible for work authorization sponsorship.

Summary:

The Data Science Lead will serve as the strategic architect and research pioneer for the organization’s data ecosystem. This role is responsible for designing robust data architectures, leading research and development (R D) for novel data sources, establishing rigorous analytical methodologies, and ensuring the seamless, scalable ingestion of high-quality data into downstream production solutions.

Core Pillars of Responsibility

1. Data Architecture Scalable Engineering

Blueprint Design: Design and oversee the evolution of scalable data architectures that support advanced analytics, machine learning (ML) modeling, and real-time processing.

2. R D Novel Data Source Evaluation

Exploratory Research: Scout, evaluate, and pressure-test new internal, external, and alternative data sources (e.g., synthetic data, IoT streams, third-party APIs) for predictive power and commercial viability. Lead the ideation and feature engineering for these data sources and document how it aligns to current and future data architecture designs.

Proof of Concepts (PoCs): Lead rapid prototyping and PoCs to validate new technologies, algorithms, and data structures before scaling them to production.

Vendor Partner Assessment: Technical vetting of data vendors and partners to ensure data quality, density, and seamless integration capabilities.

3. Methodology Analytical Rigor

Framework Standardization: Define and document the organization's gold-standard methodologies for statistical analysis, experimental design (A/B testing), and ML modeling.

Evaluation Metrics: Establish rigorous validation protocols and evaluation metrics (e.g., precision/recall, drift detection, bias/fairness audits) to ensure model and data integrity.

Continuous Improvement: Keep the organization at the cutting edge of data science by translating academic research and emerging industry trends into practical business methodologies.

4. Ingestion Solution Integration

Productionalization Bridge: Serve as the critical bridge between R D and Production, ensuring that complex analytical models and data sources are seamlessly ingested into core business products and solutions.

API Interface Design: Oversee data delivery contracts between the DS ecosystem and downstream software applications to ensure the creation of clean, well-documented APIs.

Key Deliverables (First 12 Months)

Data Source Playbook: A formalized framework for scoring, vetting, and onboarding new data assets.

Methodology Registry: A centralized repository of approved statistical models, evaluation metrics, and ingestion protocols to ensure team-wide consistency.

Feature Importance Registry Feature Engineering Roadmap: a centralized repository connecting current data sources to their product value and impact of removal and/or possible substitutes to the roadmap of how Prove can leverage the signals in new and differentiated ways

Architectural Roadmap: A 12 month to 3-year vision aligning data science infrastructure with corporate scaling goals.

Profile Qualifications

6+ years in Data Science/Data Engineering, with at least 2 years in a technical leadership or architectural role.

Technical Stack

Python, R, SQL, Cloud Platforms (AWS/GCP/Azure), Big Data tech (Spark, Kafka), Orchestration (Airflow), and MLOps tools.

Expertise

Deep understanding of data modeling, schema design (SQL/NoSQL), statistical evaluation, and MLOps deployment patterns, especially in R D functions that bridge research with production.

Soft Skills

Exceptional ability to translate complex technical architectures into strategic business va…