Вакансия из Hirify Global, списка международных tech-компаний Для мэтча и отклика нужен Plus
Пожаловаться
Зарплата и рынок
развернуть
По международному рынку данных пока нет
На СНГ рынке: $5.1к/мес ($3.9к - $5.9к)
84
Хорошая вакансия
развернуть
Чётко описана роль уровня Staff с ответственностью за специализированный production-продукт, но сочетание глубокой статистики, entity resolution и платформенных задач может сделать её требовательной.
?Широкая зона ответственности
Современный стек
Понятная ответственность
Много самостоятельности
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Staff Data Scientist (Tech Lead) (Entity Resolution/Record Linkage): Building and operating probabilistic matching pipelines that link large, messy consumer datasets with an accent on entity resolution, sampling statistics, uncertainty quantification, and production reliability. Focus on designing scalable methodology, managing versioned changes and trend continuity, and partnering with Engineering on cost-efficient deployment across Python, BigQuery, dbt, and GCP.
Location: LATAM
Company
hirify.global is a fast-growing U.S. data and analytics company building recurring data products from large consumer datasets.
What you will do
Own and evolve the probabilistic matching algorithm, including eligibility logic, sample sizes, match windows, confidence scoring, and production reproducibility.
Run the recurring matching process end to end while improving match quality, runtime, and cost.
Investigate model interactions, conflicts, and second-order effects.
Partner with Engineering on architecture, deployment, scaling, and MLOps across dbt, BigQuery, and GCP.
Own methodology documentation, versioning, restatements, and trend continuity for clients.
Mentor teammates and present methodology decisions and trade-offs to senior leadership.
Requirements
7–10 years of experience in data science or applied science, including ownership of production systems rather than research only.
Experience reconciling or matching large, messy, multi-source consumer datasets.
Deep expertise in entity resolution and record linkage, including blocking strategies, probabilistic matching such as Fellegi-Sunter, confidence scoring, and precision/recall trade-offs.
Strong panel and sampling statistics, including weighting, raking, bias correction, and minimum reporting thresholds for small samples.
Experience with confidence intervals, bootstrapping, and distinguishing real period-over-period changes from noise.
Expert production-grade Python with OOP, testing, and maintainable code, plus strong SQL on BigQuery.
Hands-on experience with dbt and large-scale processing using Spark, PySpark, Dask, or similar.
Solid cloud experience, ideally GCP, plus MLOps fundamentals including CI/CD, monitoring, and reproducibility.
Experience managing methodology changes in recurring data products, excellent written and spoken English, daily use of AI coding tools, and experience mentoring or informally leading individual contributors.
Nice to have
Privacy-preserving matching, including PII handling, hashing, tokenization, and clean-room patterns.
Data quality monitoring, including dbt tests, anomaly and drift detection, and data contracts.
BigQuery cost engineering, including partitioning, clustering, and slot usage.
Temporal and session data experience, including sessionization and timestamp alignment across sources.
Docker and Kubernetes deployment ownership.
Media-measurement or consumer panel dataset experience.
Culture & Benefits
Full-time, high-autonomy role focused on recurring client deliverables.
Pragmatic decision-making prioritizes scalable, cost-efficient, and resilient solutions.
Close collaboration with Engineering and direct communication with senior leadership.
Будьте осторожны
Если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого. Это мошенники. Обязательно жмите «Пожаловаться» или пишите в поддержку. Подробнее в гайде →