Чётко очерченная senior-роль на стыке ML в продакшене, безопасности и AI, с хорошими льготами и поддержкой обучения; важно учитывать небольшую команду и ограничение удалённой работы Францией.
?Небольшая команда
Актуальный стек
Сильный AI-домен
Поддержка обучения
?Работа только из Франции
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Senior Software/Data Engineer (Bot Detection): Building production detection pipelines and models for identifying automated abuse across large-scale traffic, account, and behavioral data with an accent on anomaly detection, graph-based analysis, and adversarial machine learning. Focus on designing feedback loops, investigating bot campaigns, measuring attacker adaptation, and balancing detection accuracy with privacy and legitimate automation.
Location: Remote from France
Company
Hugging Face builds an open-source platform and ecosystem for AI builders, hosting models, datasets, and applications for a large developer community.
What you will do
Build and operate detection pipelines using large-scale traffic, session, account, repository interaction, and API data.
Develop and deploy anomaly detection, clustering, graph-based approaches, supervised classifiers, and other detection heuristics.
Define client and network features with the signals-focused bot-detection engineer and assess their robustness against attacker adaptation.
Build labeling, evaluation, false-positive monitoring, dashboards, and alerting feedback loops.
Investigate fake-account waves, metric inflation, and large-scale scraping, converting findings into durable production detections.
Maintain proportionate, privacy-respecting enforcement that minimizes impact on legitimate users and automated workloads such as CI, research crawlers, and integrations.
Requirements
Strong production experience applying data science or machine learning to adversarial problems such as bot detection, fraud, abuse, spam, or security analytics.
Fluency in Python and SQL, with experience using large-scale data tooling such as Spark, ClickHouse, BigQuery, or similar.
Experience taking models or detection logic from exploration to production and maintaining them over time.
Strong understanding of web traffic and network data, including how signals can be spoofed.
Ability to evaluate precision/recall trade-offs, attacker adaptation, and operational cost rather than relying only on offline metrics.
Pragmatic and autonomous approach, with willingness to work closely with one or two people in a fast-moving team.
Nice to have
Published work on bot detection, web measurement, or adversarial machine learning; a PhD is welcome but not required.
Experience with graph analytics or streaming detection.
Familiarity with the machine learning and open-source ecosystem and the Hugging Face Hub.
Culture & Benefits
Remote work with flexible working hours; employees can visit the offices in New York and Paris.
Health, dental, and vision benefits for employees and dependents, plus parental leave and flexible paid time off.
Reimbursement for relevant conferences, training, and education.
Workstation equipment support when needed and company equity for all employees.
Inclusive, distributed workplace supporting collaboration across the machine learning and artificial intelligence community.
Hiring process
Start the answer to the first application question with “GPU-poor and proud 🤗”.
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 →