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: $5.3к/мес ($4к - $6к)
84
Хорошая вакансия
развернуть
Вакансия предлагает понятную ответственность за масштабные рекомендательные системы и работу с генеративным ИИ, но криптовалютная сфера и работа в офисе в Куала-Лумпуре могут быть важными компромиссами.
Криптосфера
Современный ML
Большой масштаб
Поддержка обучения
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Senior Recommendation Algorithm Engineer (AI) (recommendation systems/fintech): Developing and optimizing recommendation models for trading products, content, and community platforms with an accent on cross-domain transfer learning, multi-objective ranking, and user behavior modeling. Focus on solving cold-start and sparse-feedback challenges, building reusable user representations, and integrating generative recommendation methods with discriminative pipelines.
Location: Kuala Lumpur, Malaysia — Kuala Lumpur Tech Office
Company
hirify.global is a cryptocurrency exchange and digital financial platform serving more than 80 million users across over 200 countries and regions, with products spanning trading, payments, wealth management, custody, institutional services, and Web3.
What you will do
Develop and optimize recommendation models for trading products, content, and community experiences using large-scale behavioral data.
Design cross-domain transfer learning and cold-start strategies for different business scenarios.
Build multi-objective ranking models optimizing CTR, CVR, LTV, and other outcomes while balancing short-term and long-term value.
Model cross-scenario user behavior, short- and long-term interests, and intent changes through reusable user representations.
Explore generative recommendation methods, including semantic IDs and generative candidate generation, and integrate them with discriminative pipelines.
Requirements
At least four years of experience developing search, advertising, or recommendation algorithms at a consumer-facing internet company, including candidate retrieval, ranking, and multi-objective modeling.
Strong computer science fundamentals and proficiency in at least one of Python, Java, or C++.
Strong software design and coding practices with a willingness to solve challenging technical problems.
Strong analytical and logical thinking, including the ability to identify problems and opportunities through data.
Interest in emerging technologies and the ability to approach complex problems with clarity and sound reasoning.
Strong business judgment, communication, and collaboration skills, including the ability to translate business needs into technical solutions.
Nice to have
Search, advertising, or recommendation algorithm experience at major technology companies such as ByteDance, Alibaba, Tencent, Meituan, Kuaishou, or Xiaohongshu.
Experience with multi-objective modeling, short- and long-term user sequence modeling, personalized uplift modeling, or generative modeling.
Publications at leading international conferences such as KDD, SIGIR, RecSys, ACL, or NeurIPS.
Hands-on experience bringing LLM or agent applications into production for search, advertising, or recommendation use cases.
Culture & Benefits
Work on multi-domain personalization across trading products, market intelligence, community content, campaigns, and AI-powered investment workflows.
Build recommendation systems at global scale for more than 80 million users across over 200 countries and regions.
Work at the intersection of traditional recommendation systems, generative AI, and LLM agents.
Access a Study Growth Fund supporting professional development and continuous learning.
Participate in internal events, workshops, global collaboration, career advancement, and internal mobility opportunities.
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 →