Senior Data Scientist

Posh • New York, NY

20d • Onsite

About The Position

We are looking for an experienced Senior Data Scientist to build the foundation of our personalization and recommendation system. In this role, you’ll lead the development of our core personalization algorithm. As one of the early data hires at Posh, you’ll shape the technical direction of our modeling strategy and set the standards for how data is defined, collected, and transformed across the organization. You’ll work across the full ML lifecycle: identifying new data sources, building clean pipelines for model features, model selection/iteration, and evaluating model performance. Your work will directly drive key product experiences, influencing ranking, classification, and personalization at scale. You’ll partner closely with Product and Engineering to define feature requirements, ensure proper tracking, and architect model-ready datasets that reflect real user behavior. You’ll establish best practices for data quality, governance, and documentation, ensuring our models remain trustworthy and performant as we grow. This role offers a high-growth opportunity as we expand our data capabilities and team. If you're passionate about building from 0 to 1 and making a lasting impact, this is the role for you. This is an in-person position at our New York City office, located in the heart of SoHo.

Requirements

• Possesses 5+ Years of full time Data Experience: Has at least 5 years of hands-on experience in data science or analytics engineering. Demonstrates a strong ability to design, build, and optimize scalable data systems.
• Expert in SQL and Python: Demonstrates strong proficiency in SQL and Python, with deep experience cleaning data, engineering features, and building efficient, production-ready modeling pipelines.
• Strong Ability to Analyze and Evaluate Models: Skilled in designing experiments, interpreting model performance, and communicating insights clearly to both technical and non-technical stakeholders.
• Experience Building Personalization and Recommendation Systems: Has built or contributed to ranking, classification, recommendation, or personalized user experience models in production environments.
• Proficient with Modern Data and ML Tooling: Experienced working with cloud data platforms and analytics tooling, and familiar with best practices in data modeling, pipeline reliability, and ML optimization.
• Has a Background in Early Stage Data Team (Required): Exhibits high interest in startups and has experience building the early foundation of a data team at a small tech company.

Nice To Haves

• Cloud ML Tools & Consumer Scale (Bonus): Experience with AWS Personalize, SageMaker, or similar cloud ML platforms, and/or working on consumer-facing products operating at scale.

Responsibilities

• Designing and Preparing High-Quality Data for Personalization Models: Own the process of data cleaning, feature selection, and model selection to build a high-performing personalization model. Ensure all inputs into personalization algorithms are reliable, well-structured, and optimized for downstream ML performance.
• Building and Maintaining Scalable Pipelines for Modeling Data: Develop robust ETL/ELT pipelines that transform raw behavioral, transactional, and catalog data into features for recommendation systems. Continuously iterate to improve data freshness and coverage using SQL and Python.
• Optimizing Infrastructure to Support ML Personalization at Scale: Enhance data architecture and processing frameworks to support real-time and batch modeling needs.
• Ensuring Strong Data Governance and Documentation: Implement best practices for data quality, documentation, observability, and lineage across all model-bound datasets.
• Collaborating with Product and Engineering on Instrumentation & Feature Tracking: Work closely with Engineering to ensure accurate tracking and logging of user actions and product interactions needed for personalization systems. Partner with Product to translate business needs into feature definitions and modeling requirements.
• Optimizing Classification Models: Develop, refine, and optimize classification models that accurately categorize events. Improve signal quality through feature engineering, tuning, sampling, and continuous iteration to ensure accurate tagging that powers downstream personalization algorithms.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Education Level: No Education Listed
• Number of Employees: 11-50 employees