Назад
13 дней назад

Senior Staff Algorithm Engineer (Recommendation)

Тип работы
fulltime
Грейд
senior
Английский
b2
Вакансия из списка Hirify.GlobalВакансия из Hirify Global, списка международных tech-компаний
Для мэтча и отклика нужен Plus

Мэтч & Сопровод

Для мэтча с этой вакансией нужен Plus

Описание вакансии

Текст:
/

TL;DR

Senior Staff Algorithm Engineer (Recommendation): Developing a next-generation social feed recommendation system for a leading crypto exchange with an accent on ranking models and user intent frameworks. Focus on evolving Transformer-based ranking toward generative recommendations and integrating LLM Agent frameworks.

Location: APAC

Company

OKX is a leading crypto exchange and developer of OKX Wallet, providing millions of users and institutions access to crypto trading and decentralized applications.

What you will do

  • Own the technical direction of the next-generation social feed recommendation engine.
  • Drive continuous ranking model iteration to improve user retention and trading conversion.
  • Build a cross-domain intent framework spanning content consumption, feature usage, and search.
  • Execute a 12–24 month roadmap evolving Transformer-based ranking toward generative recommendation.
  • Integrate recommendation and search capabilities into an LLM Agent framework for proactive intent fulfillment.

Requirements

  • Master's or PhD in CS/Math with 8+ years of experience, including 5+ years in core recommendation or search roles.
  • Track record of owning end-to-end recommendation pipelines at 10M+ DAU scale.
  • Deep expertise in Attention mechanisms, sequential behavior modeling, and Listwise losses.
  • Expert-level knowledge of MMoE, PLE, ESMM and gradient conflict mitigation.
  • Hands-on experience with Uplift Modeling, Position/Selection Bias correction, and probability calibration.
  • Proficiency in large-scale distributed training (10B+ parameters) and real-time feature engineering using Flink and Kafka.

Nice to have

  • Knowledge of Semantic Tokenization (FSQ/RQ-VAE) and RLHF/DPO applied to recommendation systems.
  • Engineering experience with LLM Agent frameworks (Tool Use/ReAct).
  • First-author publications at RecSys, KDD, or WWW.
  • Experience with Bandit/RL production deployment or a background in fintech/crypto.

Culture & Benefits

  • Competitive total compensation package.
  • L&D programs and education subsidies for professional growth.
  • Comprehensive healthcare schemes for employees and dependants.
  • Wellness and meal allowances.
  • Regular team building programs and company events.

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 →