Technology
Staff Data Scientist (Tech lead)
DevSavant Inc.
Ashby
- Location
- LATAM, Not specified
- Type
- FullTime
- Salary
- Salary not specified
- Posted
- 20 Nov 2026
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,
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.