Position Summary:

The Lead Data Scientist is a subject matter expert that will provide advice on technical issues, business issues, and team operations. This position will report directly to the Sr. Director of Data Science, will actively lead projects, write production quality code, deploy models, mentor individuals on the Data Science Team, and regularly find ways to improve team dynamics. The Lead Data Scientist is a key contributor to data science strategy and can solve unique problems. This role will help recruit top talent. 

Essential Job Functions:

• Ownership and leadership in two major verticals within the data science team such as Product Data Science, Personalization, or Fraud Detection.
• Provide technical and thought leadership for the data science team
• Can present to a wide audience
• Accountable for the quality and design of the systems built while providing guidance
• Partner with department head on technical direction and strategy
• Bring business context to decisions made across teams
• Provide exemplary architectures in terms of robustness, stability, scalability and cost-effectiveness
• Continuously decompose complex problems into simple, straight-forward solutions
• Suggest appropriate algorithms for specific technical challenges at hand, and lead team members to implement and tune the algorithms
• Consultant and technical expert in high-stakes projects
• Flexibly apply ETL best practices, identify and resolve challenges long-term in key stages
• Actively mentor individuals on advanced data science techniques
• Regularly examine team culture looking for ways to improve team dynamics
• Contribute to Truckstop’s intellectual property
• Key contributor to engineering strategy and large projects
• Participate with the external technical community
• Write production quality code, APIs, and data pipelines
• Train and deploy statistical and machine learning models
• Design and measure experiments
• Bring actionable and thoughtful solutions / recommendations to roadblocks
• Participate in hiring process by interviewing and making recommendations 
• Use causal reasoning to triage problems
• Document postmortem

Position Requirements:

• MS or PhD in Computer Science, Math, Physics or related field, and 5-9 years of data science experience. PhD strongly preferred, but will evaluate relevant experience MS in lieu of a PhD
• Strong experience in building practical, efficient, accurate, reliable, and scalable data science models
• Strong understanding of data architecture fundamentals 
• Fluency in machine learning algorithms for supervised and unsupervised scenario
• Understanding of the business value of data problems
• Deeply understand the construction of user centric tracking and segmentation systems or similar experiences
• Deep understanding of the limitations of various algorithms and suggesting appropriate algorithms for specific technical challenges at hand, and leading team members to implement and tune the algorithms
• Considering the time and space complexity of algorithms and implementation of complete algorithms
• Applying multi-source attribution models to analyze importance of product features
• Understand ETL best practices, identifying and resolving challenges long-term in key stages
• Expert in Linux, familiar with command line operations
• Expert in Python
• Architect API based modules and lead team to develop these implementations in parallel with collaborating teams