Senior Lead Data Scientist, Graph & Forecasting

This is a fully remote position, open to applicants in United States.

📋 Description

• Spearhead the development of predictive intelligence capabilities that drive operational, commercial, and product decisions.

• Create and enhance graph-based representations of Dynata's data assets.

• Construct predictive models aimed at improving critical business outcomes.

• Guarantee that analytical models are robust, scalable, and ready for production.

• Collaborate with product, engineering, and platform teams on identity resolution, feasibility forecasting, panel health monitoring, audience intelligence, dynamic pricing, and operational optimization.

• Design and refine graph-based data models for audience intelligence, project similarity analysis, clustering, and relationship-driven analytics.

• Build and sustain resilient identity resolution frameworks utilizing both deterministic and probabilistic matching techniques.

• Develop graph structures that support downstream analytics, forecasting, optimization, and AI applications.

• Assess graph performance, scalability, and business impact.

• Create and manage forecasting models for supply prediction, incidence estimation, completion probability, panel health, and other critical business scenarios.

• Formulate time-series and predictive models that consider respondent behavior, market dynamics, and operational conditions.

• Expand forecasting methodologies for scenario analysis, optimization, and decision support.

• Oversee model performance and pinpoint opportunities for continuous improvement.

• Design and implement validation strategies to evaluate accuracy, stability, scalability, and operational readiness.

• Establish best practices for model evaluation, experimentation, monitoring, and governance.

• Act as the technical authority for graph analytics, forecasting methodologies, and production-grade machine learning.

• Ensure that solutions deliver long-term maintainability, performance, and business value.

• Collaborate on schema design, feature engineering strategies, and data contracts.

• Transform complex analytical findings into actionable business recommendations.

• Influence stakeholders regarding analytical investments, priorities, and roadmap decisions.

⛳️ Requirements

• 8+ years of practical experience in data science, applied machine learning, analytics, or related areas.

• Established experience in developing and deploying graph analytics, machine learning, or predictive modeling solutions in production settings.

• Extensive knowledge in graph analytics, including graph databases, graph algorithms, similarity modeling, clustering, and network analysis.

• Strong experience with graph technologies like Neptune, Neo4j, TigerGraph, or similar platforms.

• Solid background in forecasting, time-series analysis, statistical modeling, and predictive analytics.

• Advanced proficiency in Python and modern data science tools.

• Experience handling large-scale, noisy, real-world operational datasets.

• Proven ability to make complex technical decisions and function effectively in ambiguous problem spaces.

• Excellent communication skills with the capability to explain intricate analytical concepts to both technical and non-technical stakeholders.

• Experience working collaboratively with product, engineering, and platform teams to deliver production-ready solutions.

• Preferred: Experience with identity resolution, entity resolution, master data management, or identity graph development.

• Preferred: Experience applying graph analytics to similarity modeling, community detection, clustering, relationship discovery, recommendation, and graph embeddings.

• Preferred: Experience in forecasting, trend and seasonality detection, anomaly and change-point detection, cohort evolution, longitudinal measurement, and demand planning.

• Preferred: Experience in market research, panel data, audience measurement, advertising technology, marketplaces, or related sectors.

• Preferred: Experience with cloud-native analytics and machine learning environments, particularly within the AWS ecosystem.

• Preferred: Familiarity with optimization, simulation, or decision-support systems.

🏝️ Benefits

• A discretionary incentive program may be included as part of the compensation package.

• Comprehensive medical and other benefits, contingent on full-time employment status.

• An inclusive and accessible work environment.

• Accommodations available upon request for all aspects of the selection process.