Вакансия из Hirify Global, списка международных tech-компаний Для мэтча и отклика нужен Plus
Пожаловаться
Зарплата и рынок
развернуть
$141к-232к/год
$200к$220кмедиана$270к
По похожим ролям (50) ~ $220к/год
На СНГ рынке: $4.7к/мес ($4к - $6.5к)
87
Хорошая вакансия
развернуть
Чёткая ответственность за ML-модели от разработки до продакшена и заметное влияние на продукт делают роль сильной, хотя участие в дежурствах добавляет операционную нагрузку.
Дежурства
Современный стек
Заметная ответственность
Антифрод в рекламе
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Senior Machine Learning Engineer, Ads (Fraud Detection/Ad Tech): Building and operating real-time fraud detection models, labeled datasets, feature pipelines, and ML serving infrastructure for Unity's Offerwall and Rewards products with an accent on anomaly detection, device risk scoring, and low-latency production systems. Focus on modernizing training and serving platforms, detecting evolving fraud patterns, and maintaining reliable model and feature monitoring.
Location: Mountain View, CA, USA, or San Francisco, CA, USA
Base salary range: $140,700–$232,300 annually, depending on work location and other factors.
Company
hirify.global develops a leading game engine and provides technology for games, XR, web experiences, and 3D applications across industries.
What you will do
Take real-time anomaly detection and device risk models from development into production to support payout and blocking decisions.
Build and maintain a labeled fraud dataset, evaluation methodology, and baseline fraud-efficacy metrics.
Design and evolve streaming and batch features for the Redis online feature store, partnering with data engineering on freshness, correctness, and lineage.
Modernize the training and serving stack, including evaluating migration from SageMaker to Kubeflow and KServe while maintaining low scoring latency.
Investigate fraud spikes and user/device behavior to develop new signals, features, and models.
Monitor production model and feature health, document runbooks and data lineage, and participate in on-call for the fraud detection stack.
Requirements
Several years of experience building ML models through production deployment, monitoring, and post-launch iteration.
Hands-on experience with fraud detection, abuse prevention, risk scoring, or anomaly detection, including sparse, noisy, or adversarial labels.
Experience with low-latency model serving and online/offline feature pipelines, such as Redis or another online feature store, Kafka or similar streaming systems, and Airflow.
Ability to build labeled datasets from imperfect signals and design evaluation methods that remain effective as fraud patterns shift.
Strong Python and SQL skills.
Working knowledge of a cloud ML platform such as AWS SageMaker, Kubeflow, or KServe.
Ability to take ambiguous problems to shipped outcomes with limited oversight, document decisions, and collaborate with backend, data, and product partners.
Use of AI coding tools to improve development speed.
Sufficient English proficiency for frequent professional verbal and written communication with colleagues and partners worldwide.
Nice to have
Experience with ad fraud, install or attribution fraud, or fraud in rewarded or incentivized advertising.
Experience with unsupervised or semi-supervised methods such as autoencoders, isolation forests, or graph-based device and user linking.
Experience migrating ML serving platforms or building MLOps tooling on Kubernetes.
Background in mobile ad tech, mobile games, or app monetization.
Culture & Benefits
Full-time employment with benefits varying by country and employment status.
Health, life, and disability insurance, retirement or pension plans, vacation and personal days, and parental and family-care programs.
Employee stock ownership, commute subsidy, office food and snacks, mental health support, and a global employee assistance program.
Training and development programs, employee resource groups, and volunteering and donation matching.
Inclusive equal-opporthirify.global workplace with interview accommodations available for candidates with disabilities.
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 →