Job Description
This job was selected by the SpringCube team to help AI, Data and Cloud Engineers discover relevant San Francisco Bay Area employers. Sign up to view the full employer details and apply directly with the hiring company.
Company Overview
A media intelligence company provides real-time insights into what audiences are watching, reading, and engaging with across screens. Its large-scale data asset is built from consented audience information and provides a comprehensive view of consumer attention, helping leading global brands make data-driven decisions.
Key Responsibilities
- Write and own production-quality Python code that is well-structured, tested, documented, and maintainable.
- Use PySpark to work with large-scale viewership datasets containing billions of rows.
- Design, build, and deploy measurement models and statistical frameworks supporting campaign measurement, reach and frequency estimation, and cross-platform attribution products.
- Select appropriate statistical and machine learning techniques based on specific business and measurement problems.
- Apply hierarchical models, Bayesian inference, gradient boosting, regularized regression, causal machine learning, and probabilistic record linkage where appropriate.
- Build and evaluate multi-touch and multi-channel attribution models.
- Apply causal machine learning techniques, including counterfactual modeling, S-learners, T-learners, X-learners, and heterogeneous treatment effect estimation.
- Partner with Data Engineering teams to define data requirements, validate pipelines, and ensure model inputs are reliable, scalable, and production-ready.
- Lead technical design reviews and contribute to architecture decisions across the Data Science team.
- Mentor junior Data Scientists through code reviews, pairing, and structured technical feedback.
- Communicate measurement methodologies, analytical findings, and model behavior clearly to technical and non-technical audiences.
- Present technical concepts and measurement insights to senior leadership and external clients.
- Own projects independently from data exploration through production delivery.
- Contribute to continuous improvement of production machine learning systems through evaluation, monitoring, and iteration.
Required Qualifications
- 5–7 years of professional data science experience with demonstrated experience delivering models and production systems.
- Expert-level Python skills with experience writing clean, modular, testable, and production-ready code.
- Advanced experience with PySpark and Databricks.
- Experience building and optimizing data pipelines and machine learning workflows using billion-row datasets.
- Deep understanding of statistics and machine learning fundamentals, including the ability to explain model behavior and methodological trade-offs.
- Strong understanding of experimental design, including A/B testing, randomization, power analysis, and appropriate applications of observational causal inference.
- Experience across the full machine learning lifecycle, including feature engineering, model evaluation, deployment pipelines, drift monitoring, and production improvement.
- Hands-on experience with uplift modeling, synthetic control, difference-in-differences, or propensity-based approaches applied to advertising or media outcomes.
- Experience with multi-touch attribution (MTA) or multi-channel attribution modeling.
- Understanding of the limitations of rule-based attribution approaches and the methodological trade-offs of data-driven alternatives.
- Hands-on experience with causal machine learning methods, including counterfactual modeling, meta-learners, and heterogeneous treatment effect estimation.
- Experience applying causal ML techniques to advertising or media measurement outcomes.
- Direct experience with TV or digital viewership data, including ACR signals, set-top-box data, viewership panels, or cross-platform measurement involving linear TV and CTV/OTT.
- Familiarity with the media measurement vendor landscape, including Nielsen, Comscore, VideoAmp, and iSpot.
- Familiarity with industry measurement standards, including MRC and GRP/TRP frameworks.
- Strong ownership mindset with the ability to independently drive projects and deliver production solutions.
- Strong communication skills and the ability to translate statistical reasoning and model behavior into actionable insights for product, engineering, and leadership teams.
- Advanced degree (MS or PhD) in Statistics, Mathematics, Computer Science, or a related quantitative field, or equivalent depth of professional experience.
Disclaimer
SpringCube curates tech job listings from various company websites to support tech professionals globally.
1.No Endorsement: Job ads on SpringCube do not imply endorsement of their authenticity or quality.
2.No Client Relationship: This company is not a client of SpringCube unless stated.
3.To Apply: Click the “Apply” button to be redirected to the hiring company’s application page for this job.
4.No Liability: SpringCube is not liable for inaccuracies.
