Portfolio Jobs

About The Team

Data Science powers Engine’s offer recommendations, dynamic pricing, and enhanced decisioning across our network. The team supports this mission by working closely with our financial partner managers and product teams to develop cutting edge models that drive value across the consumer journey through any of our complex funnels. The team constantly drives innovation in advanced analytics, experiment design and execution, while maintaining the rigor of a first class engineering and scientific team in all our products. Through this approach, we serve as a trusted partner to our internal and external stakeholders as a key advisory team.

About the Role

You’ll lead the team in building analytics and models that solve challenges in our marketplace, covering topics such as auction mechanics, real time bidding and pricing, and recommendation of diverse financial products. You’ll work hand in hand with product managers in formulating, designing, and executing large scale experiments to derive significant insights that improve our platform’s value. Your models will be used to generate direct revenue impacts in real time, and your data solutions will affect millions of American users daily. You'll have the opportunity to continuously learn and apply the latest innovations in data science, financial markets, and have an opportunity to mentor other junior members of the team.

Challenges You’ll Tackle Daily

• How can we rank financial products for each consumer to best match their needs?
• Can we derive useful signals from consumer behavior data to improve our models?
• How can we integrate third party data into our price and recommendation models?
• How do we design effective experiments to find meaningful insights with statistical significance in a noisy environment?
• How do we balance the needs of our financial partners against our lead channels and the consumer good?
• Can we design tests and metrics that better match business outcomes and KPIs?
• How can we optimize our research process to enable quicker iteration times?

Who You Are

• You have experience designing model and analytics solutions driven by client and product needs.
• You frequently collaborate with account managers and clients in stakeholder meetings, leading discovery, requirements gathering, and project scoping, which results in efficient execution and increased business trust in data science products
• You’re comfortable presenting complicated statistical concepts in a concise manner to a non-technical audience, including executive level stakeholders
• You understand a variety of ML algorithms, including: classification, regression, clustering, recommendation systems, and time series analysis
• You have worked with industry standard ML libraries in Python/Scala such as scikit-learn, XGBoost, LightGBM, Spark ML, TensorFlow/PyTorch, etc
• You have designed hypothesis tests and large scale experiments for models and related product features and are able to manage noisy data to make decisions
• You have experience building models for recommendation, price, and conversion prediction for large scale systems, in both batch and real time settings
• You have performed rigorous and cleanly organized research doing exploratory data analysis and statistical modeling for product and business teams
• You are comfortable writing clean and performant SQL queries for data exploration and feature creation from a data warehouse or traditional relational database
• You have worked jointly with engineering teams to deploy models into production
• You regularly document your work across the entire data science lifecycle
• You know that people come first, and the rest (code, analysis) follows after this

Requirements

• 4+ years of experience in a data science team designing ML models and advanced analytics for clients or client facing teams
• 3+ years of experience working with or in (not all required, this is illustrative):
  • ML platforms: Sagemaker, Spark, Ray, PyTorch, etc
  • Data warehouse (Redshift, Snowflake), relational database (Postgres, MySQL)
  • Python, SQL, in particular with a focus on analytics, ML, and visualization
  • Designed and run A/B tests and general live testing to validate product, model or analytics ideas, and are able to validate statistical significance
• 2+ years of experience working with or in (not all required, this is illustrative):
  • Application programming language such as Scala, Java, C++
  • Writing or enhancing web applications and APIs
  • Familiarity with Containerization (Docker, Kubernetes, etc)
  • Writing ETL/ELT workflows that enable advanced analysis and model building using technologies such as dbt, Airflow, etc.
• Have a solid foundation in statistics, analytics and machine learning
• Cross-functional an effective communicator with technical/nontechnical audiences
• Ability to mentor junior colleagues and lead team in performing high quality research and model development

Nice To Haves (Not Necessarily Required!)

• You have worked with systems that bid or trade on “assets” (ads, stocks, crypto) that require real time pricing, predictive, and/or recommendation models and often have dynamic feedback loops and direct monetary impact
• Have exposure to causal inference methods, probabilistic programming, optimization methods, and/or online learning models
• You regularly are present as an SME during client calls and sales pitches
• Experience building and explaining the differences of various machine learning models such as gradient boosted trees, multi-armed bandits, deep learning, etc.
• You have some experience writing web apps that serve models or advanced analytics to users (think: streamlit, flask, Plotly Dash, etc)

Location: Remote Optional, New York Preferred