statisticsllmfraud detectionmachine learningdeep learningdata pipelinescontent moderationfeature engineeringagentic ai
Вакансия из Hirify Global, списка международных tech-компаний Для мэтча и отклика нужен Plus
Пожаловаться
Зарплата и рынок
развернуть
€68к-92к/год
€80к€80кмедиана€92к
По похожим ролям (6) ~ €80к/год
На СНГ рынке: $4.5к/мес ($3.7к - $6к)
90
Крутая вакансия
развернуть
Чётко очерченная senior-роль в ML в крупной продуктовой компании сочетает работу над моделями в продакшене, влияние на стратегию и заметные возможности для развития.
Актуальные ML-задачи
Чёткая зона ответственности
Бюджет на развитие
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Senior Data Scientist (Trust & Safety) (Machine Learning/LLM): Building production machine learning models and scalable data pipelines to prioritize reports, automate moderation decisions, and protect a second-hand marketplace with an accent on adversarial content detection, real-time model deployment, and data quality. Focus on designing end-to-end ML systems, analyzing text and images, balancing quality, latency, and cost in LLM workflows, and guiding model strategy across teams.
Location: Amsterdam, Netherlands; hybrid work with 2 recommended office days per week. Remote work is available for up to 90 days per year in the EU, including 21 days globally; non-EU citizens may work worldwide for up to 21 days per year.
hirify.global operates a European marketplace for second-hand fashion and lifestyle items, with additional shipping and payment businesses across Europe.
What you will do
Lead the research, development, deployment, and continuous improvement of production machine learning models for prioritizing reports and automating actions against harmful marketplace entities at scale.
Design and refine data versioning, labeling pipelines, and data-quality processes for model training.
Collaborate with Data Infrastructure and backend engineering teams to build and maintain scalable data pipelines and ML infrastructure.
Develop models that analyze text, images, and other data formats to identify harmful or risky content and users.
Collaborate with Decision Scientists to test, assess, and improve models while contributing to the Actioning team’s strategic roadmap.
Mentor colleagues, promote ML best practices, and influence model-development strategy and cross-functional collaboration.
Requirements
4+ years of experience in data science, with a strong foundation in machine learning, statistics, or computational mathematics.
Proficiency in classical and deep learning techniques, including the use of current tools and methodologies for complex problems.
Hands-on experience building and deploying agentic AI applications or LLM-powered workflows handling large traffic while balancing quality, latency, and cost efficiency.
Deep understanding of deploying, maintaining, and scaling real-time machine learning models in production.
Experience designing and implementing data ingestion, feature engineering, and model training pipelines with engineering teams.
Strong problem-solving skills and commitment to current developments in machine learning and data science.
Ability to communicate complex technical concepts clearly to technical and non-technical stakeholders and connect technical work to business value.
Nice to have
Experience with fraud detection, harmful content detection, or another adversarial domain.
Culture & Benefits
Hybrid work model with recommended office attendance two days per week and a workation policy.
25 days of paid annual leave, work-from-home allowance, and home-office equipment support with a furniture budget of up to €540.
Learning budget starting at €3,000 per year and up to 10 working days over two years for professional development.
MacBook, public-transport NS Business Card, bike leasing, hirify.global shopping budget, team-building events, and a dog-friendly office.
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 →