Senior Data Scientist (Pistachio Team)
Role details
Job location
Tech stack
Job description
- Estimate domain traffic and engagement metrics (e.g., pages per visit, session duration) from clickstream data
- Predict the most likely referral domain for a given event
- Identify session acquisition channels (direct, organic, paid, etc.)
- Development of quantitative frameworks for supplier criticality scoring and supplier portfolio optimization
- Investigation related to supplier outages, data inconsistencies, and recovery/backfill artifacts
- Design of proactive supplier risk mitigation approaches to minimize the impact of external data disruptions on customer-facing metrics
- Identify socio-demographic characteristics of domain audiences to build detailed user profiles
- Domain categorization by topic, industry, business type, and other attributes
- URL analysis, including clustering and classification tasks, The Pistachio team is part of the AI & ML Research Department. We develop machine learning solutions that provide data for the Traffic & Market Toolkit, including website traffic and market analytics. The results of our work are used to generate reports, power widgets, and support analytical products. We work with large-scale data and apply machine learning to improve data quality, coverage and accuracy.
We treat data as a product, and that's why we constantly work to improve it and make it better for the users of Traffic & Market products while making better assumptions based on it.
We are looking for a Senior Data Scientist who can take ownership of complex, ambiguous problems and drive them from idea to production impact. This role requires both strong technical expertise and a proactive, collaborative mindset.
We value people who naturally create clarity around their work, build trust through transparent communication, and become a driving force behind initiatives rather than waiting for direction.
You will work closely with engineers, product managers, and business stakeholders to develop scalable data-driven solutions and influence how we make decisions as a team.
Our Stack
- Google Cloud Platform;
- Data Storage: ClickHouse
- Language: Python;
- Tech stack: Airflow, Grafana, MLFlow, LangFuse
- Developer tooling: GitLab CI/CD, Docker, Jupyter, Claude Code/Codex, Streamlit
About The Perks
- Unlimited PTO
- Hobby & team building budget allowance
- Employee Support Program
- Loss of family member financial aid
- Employee Resource Groups
Requirements
Move together. Raise the bar. Learn fast-grow faster. That's the default. And here's what else is needed to succeed in this role:
Hard Skills
- Strong practical experience in Data Science, Machine Learning, or Applied Statistics
- Solid understanding of experimentation, hypothesis validation, and metrics-driven decision making
- Excellent Python skills and experience building production-oriented solutions
- Understanding of software engineering best practices: testing, reproducibility, and code quality
- Strong SQL knowledge and experience working with analytical databases
- Experience working with large-scale datasets and data pipelines
Soft Skills
- Takes ownership in ambiguous environments and proactively drives initiatives forward
- Creates transparency around progress, risks, and decisions
- Builds trust through reliable delivery and clear communication
- Strong collaboration skills and ability to align stakeholders with different perspectives
- Able to independently structure problems and break down complex challenges into actionable steps
- Comfortable working in a fast-changing environment and adapting to evolving priorities, requirements, and business needs
Not Required, But a Plus
- Experience working with clickstream or behavioral data
- Experience with traffic prediction or user analytics
- Familiarity with ClickHouse or other column-oriented databases
- Experience designing data-intensive services together with backend/data engineers