Назад
Company hidden
обновлено 2 месяца назад

Data Scientist (Search & Recommendations)

Формат работы
onsite
Тип работы
fulltime
Грейд
senior
Английский
b2
Страна
Cyprus
Релокация
Cyprus
Вакансия из списка Hirify.GlobalВакансия из Hirify RU Global, списка компаний с восточно-европейскими корнями
Для мэтча и отклика нужен Plus

Мэтч & Сопровод

Для мэтча с этой вакансией нужен Plus

Описание вакансии

Текст:
/
TL;DR
Data Scientist (Search & Recommendations) (Search, Ranking, Recommendation Systems): Building and optimizing retrieval, ranking, and recommendation pipelines for high-load, real-time production systems with an accent on search relevance, learning-to-rank, behavioral features, and multi-stage retrieval. Focus on designing offline and online experiments, solving low-latency inference challenges, and connecting model quality with product and business outcomes.

Location: Cyprus, with relocation to Limassol and a 3-year Cyprus work visa

Company

hirify.global is a technology company building high-load products used by millions of people worldwide, including real-time entertainment solutions for a global audience.

What you will do

  • Develop and improve retrieval pipelines for large-scale production search systems, including candidate generation, query processing, matching, filtering, and hybrid lexical-semantic retrieval.
  • Build, train, and optimize ranking models for search and recommendation systems using behavioral, content-based, contextual, and real-time features.
  • Develop multi-stage recommendation pipelines for related-item, complementary-item, next-action, and behavioral use cases.
  • Design and analyze offline and online experiments, including A/B tests using relevance, engagement, conversion, retention, and revenue metrics.
  • Build end-to-end ML pipelines for feature generation, training, validation, deployment, and monitoring.
  • Collaborate with product, backend, data engineering, and MLOps teams to productionize ML solutions for high-load, low-latency systems.

Requirements

  • Hands-on experience building production search, ranking, or recommendation systems.
  • Strong Python and SQL skills for machine learning, data processing, and analytical queries.
  • Practical experience with learning-to-rank, candidate retrieval, search relevance, or recommender-system modeling.
  • Experience building and evaluating multi-stage retrieval and ranking pipelines, including metrics such as Precision, Recall, NDCG, MAP, MRR, CTR, and conversion.
  • Experience with feature engineering, behavioral data, large-scale production systems, distributed data processing, analytical databases, and streaming platforms.
  • Relocation to Cyprus is supported, including a Cyprus work visa and assistance for the candidate's family.

Nice to have

  • Experience with Elasticsearch, OpenSearch, Solr, Lucene, vector databases, approximate nearest neighbor search, or hybrid retrieval.
  • Experience with query understanding, classification, spell correction, synonyms, or query expansion.
  • Experience with DSSM, two-tower models, BERT-based ranking, cross-encoders, Airflow, or MLflow.

Culture & Benefits

  • EU-based employment contract with a full relocation package, including flights and a company-covered apartment for the first month.
  • Private medical insurance for the employee and family, a corporate mobile plan, and interest-free support for car purchases.
  • Provident fund, performance reviews twice a year, bonus opportunities, and salary adjustments.
  • Well-being support, psychological assistance with 50% coverage, sports benefits, and family education support covering 50% of school and kindergarten fees.
  • Paid language courses and development programs, including conferences, training, and coaching.
  • Fully equipped office in Limassol city center with free catering, coffee bar, health bar, team buildings, and hackathons.

Hiring process

  • HR interview: 40 minutes.
  • Technical interview: 1.5 hours.
  • Final interview: 45 minutes.

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 →