About the role
We’re looking for a Staff Data Scientist to join a fast-growing U.S. data and analytics company. You’ll own one of the hardest problems in the business: matching records across large, independent consumer datasets that were never designed to join, and turning incomplete, noisy data into numbers clients trust.
This is a high-autonomy role. You’ll take loosely scoped problems and drive them to validated, production-ready solutions. You’ll also partner closely with Engineering and be the person the team brings its hardest questions to.
What you’ll do
Own and evolve the core matching algorithm that probabilistically links two independent datasets, including sample size, match-window design and reproducibility of the production pipeline.
Own eligibility logic: decide which records qualify for matching and reporting, balancing data quality against reach and sample size.
Run the recurring matching process end to end, improving match quality and runtime cost over time.
Investigate and resolve cases where models interact or conflict, including unexpected second-order effects.
Partner with Engineering on how models are architected, deployed and scaled (dbt, BigQuery, GCP), treating cost and runtime as seriously as accuracy.
Own the written methodology: design docs, decision records and version history.
Lead methodology change management: decide when a change requires restating history, version each release, and protect trend continuity for clients.
Mentor teammates on investigation methods and code quality.
Present methodology decisions and trade-offs directly to senior leadership.
What you’ll bring
7–10 years in data science or applied science, with real ownership of production systems, not just research.
Experience reconciling or matching large, messy, multi-source consumer datasets, such as identity graphs, credit or enrichment data, clean-room data, or fraud and identity work.
Deep expertise in entity resolution and record linkage: blocking strategies, probabilistic matching (e.g., Fellegi-Sunter), match-confidence scoring and precision/recall trade-offs.
Strong panel and sampling statistics: weighting and raking, bias correction, and minimum reporting thresholds for small samples.
Uncertainty quantification with confidence intervals and bootstrapping, and the ability to tell a real period-over-period change from noise.
Expert, production-grade Python (OOP, tested, maintainable) and strong SQL on BigQuery.
Hands-on experience with dbt and large-scale processing (Spark/PySpark, Dask or similar).
Solid cloud experience, ideally GCP (Dataproc, Cloud Run, Cloud Build, GKE), plus MLOps fundamentals: CI/CD for data and ML pipelines, monitoring and reproducibility.
Experience managing methodology changes in a recurring data product (restatements, versioning, trend continuity).
A pragmatic mindset: in a business built on recurring deliverables, the right fix is often the scalable, cost-efficient and resilient one.
Daily use of AI coding tools (Claude Code, Cursor or similar), while owning every line you ship.
Excellent written and spoken English, with the ability to explain complex solutions to non-technical audiences.
Experience mentoring or informally leading other individual contributors.
Nice to have
Privacy-preserving matching: PII handling, hashing and tokenization, clean-room patterns.
Data quality monitoring: dbt tests, anomaly and drift detection, data contracts.
BigQuery cost engineering: partitioning, clustering and slot usage.
Temporal and session data: sessionization, aligning timestamps across sources, time-zone issues.
Docker and Kubernetes at a deployment-ownership level.
Experience with media-measurement or consumer panel datasets.
Skills Required
- 7-10 years of experience in data science or applied science
- Production ownership of data science systems
- Experience matching or reconciling large, messy, multi-source consumer datasets
- Expertise in entity resolution and record linkage, including blocking strategies and probabilistic matching
- Experience with match-confidence scoring and precision/recall trade-offs
- Strong panel and sampling statistics, including weighting, raking, bias correction, and minimum reporting thresholds
- Experience with confidence intervals, bootstrapping, and uncertainty quantification
- Expert production-grade Python and strong SQL on BigQuery
- Hands-on experience with dbt and large-scale processing using Spark, PySpark, Dask, or similar
- Solid cloud experience, ideally GCP
- MLOps fundamentals, including CI/CD, pipeline monitoring, and reproducibility
- Experience managing methodology changes, restatements, versioning, and trend continuity
- Daily use of AI coding tools such as Claude Code or Cursor
- Excellent written and spoken English
- Experience mentoring or informally leading individual contributors
- Privacy-preserving matching experience, including PII handling, hashing, tokenization, or clean-room patterns
- Data quality monitoring experience, including dbt tests, anomaly detection, drift detection, or data contracts
- BigQuery cost engineering experience with partitioning, clustering, or slot usage
- Experience with temporal and session data, timestamp alignment, or time-zone issues
- Docker and Kubernetes deployment ownership experience
- Experience with media measurement or consumer panel datasets
What We Do
DevSavant provides comprehensive technology solutions to Savant Growth's portfolio companies. Our data scientists and developers are experts in the fields of data analytics, software development, and AI. DevSavant’s engineers work across the spectrum of full-stack technology solutions for the B2B SaaS industry, helping you growing company tackle its toughest challenges and giving you the freedom to focus on what matters most, the future of your business







