Data Scientist II

Tunnl

1d • Hybrid

About The Position

As a Data Scientist II at Tunnl, you will contribute to the development and improvement of machine learning systems that power audience intelligence, targeting, and measurement across television and digital channels. You'll work within established ML patterns on well-scoped problems, with increasing independence as you grow into the role. You'll be embedded in a collaborative data science team and work closely with senior data scientists who provide technical guidance and code review. This role sits at the intersection of data science and AdTech — your work will directly affect audience targeting quality and measurement accuracy for thousands of advertisers.
In your first 6 months, you'll be successful if you: ship improvements to at least one production model with guidance from the team; can independently debug pipeline issues and model quality problems; contribute substantially to building a data science idea into a working proof of concept; and communicate clearly about your work in team reviews and cross-functional meetings.

Requirements

• 2–4 years of experience in Data Science or Machine Learning, with a track record of delivering end-to-end ML projects, or demonstrated equivalent experience through strong project work or a portfolio
• Solid grounding in statistics and probability; experience designing or analyzing experiments such as A/B tests or holdout studies
• Strong proficiency in Python and SQL
• Experience querying and processing large datasets using Spark or Databricks in a cloud environment (AWS preferred); comfort running and monitoring scheduled jobs
• Experience contributing to production ML pipelines including batch model training, scoring, and evaluation
• Familiarity with supervised classification or segmentation modeling applied to real-world datasets
• Familiarity with software engineering best practices: git, automated tests, and code review workflows
• Strong communication skills with the ability to collaborate effectively across technical and non-technical teams

Nice To Haves

• B.S. in computer science, statistics, data science, or a quantitative field; M.S. a plus but not required
• AdTech or audience intelligence experience; familiarity with audience modeling, lookalike systems, or ML-driven targeting
• Exposure to survey research methodology, including sample design, survey weighting, and bias/representativeness considerations
• Some exposure to vector similarity and approximate nearest neighbor systems (FAISS or equivalent)
• Experience with scikit-learn and XGBoost for supervised classification; familiarity with PyTorch is a plus
• Experience with data visualization tools or libraries (Matplotlib, Seaborn, Tableau, or equivalent) or comfort presenting analytical findings to non-technical audiences
• Exposure to or interest in GenAI tooling and LLM integration
• Awareness of or interest in self-supervised or representation learning approaches

Responsibilities

• Build and improve machine learning models for audience targeting, lookalike generation, and individual propensity scoring
• Contribute across the ML lifecycle — from exploratory analysis and experimentation through production deployment and monitoring, within established team patterns and with guidance from senior data scientists
• Design and analyze experiments (A/B tests, holdout studies) to evaluate model performance and measure business impact
• Translate analytical findings into clear, concise communications for technical and non-technical audiences including product and customer success teams
• Engineer features from demographic, behavioral, and identity data — including handling missing values, encoding strategies, and data quality validation
• Write well-tested, documented, and maintainable code; participate in code reviews and contribute to improving team coding standards
• Partner closely with data engineers to ensure feature pipelines are reliable and well-documented, and work with product managers to align model outputs with business requirements
• Work with distributed computing (Spark/Databricks) and cloud data platforms (AWS, Snowflake) to build and contribute to production ML pipelines

Benefits

• Excellent medical, vision, and dental coverage
• Health Savings Account (HSA) and Flexible Spending Account (FSA) options
• Employer-paid life insurance & short-term & long-term disability, with other voluntary additional coverage available (accident, critical illness, hospital indemnity)
• Flexible unlimited paid vacation
• 80 hours of paid sick leave
• 10 paid company holidays per year plus the week between Christmas and New Year’s off
• 401(k) plan with 100% match up to 3%, plus 50% match up to 5% (subject to IRS limits)
• Cell phone reimbursement stipend
• Monthly parking or commuter stipend for VA-based employees

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Education Level: High school or GED
• Number of Employees: 11-50 employees