Назад
Company hidden
1 день назад

Staff Data Scientist (Search/LLM)

Формат работы
hybrid
Тип работы
fulltime
Грейд
senior
Английский
b2
Страна
Germany
Релокация
Germany
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
Staff Data Scientist (Search/LLM): Building and optimizing deep learning ranking models for global search services across 60+ countries and 35 languages with an accent on LTR architectures, embedding-based retrieval, and agentic ML experimentation. Focus on leading ranking architecture, running autonomous overnight experiments with LLM coding agents, improving production model health, and setting technical standards across multiple teams.

Location: Berlin, Germany; hybrid work with attendance at the Berlin campus 2 days a week

Company

hirify.global operates a global local delivery platform across around 65 countries, with its headquarters in Berlin and a consumer search experience serving more than 60 countries and 35 languages.

What you will do

  • Lead search-ranking model and architecture design from offline experimentation through production using DCN-V2, MMoE, and Two-Tower architectures.
  • Lead agentic ML research with LLM coding agents such as Claude Code and Gemini, running overnight experiments and converting strong signals into production ranking gains.
  • Improve ranker quality through feature engineering, ranking signals, feature stores, embedding-based retrieval, and research-to-production implementation.
  • Set production model-health standards covering drift, latency, and feature-pipeline integrity across multiple squads.
  • Define goals with Product and Engineering leads, communicate results to stakeholders, mentor data scientists, review work, and contribute to hiring.

Requirements

  • Master’s degree in Computer Science, Mathematics, Physics, or a related quantitative field, or a Bachelor’s degree with 6+ years of work experience.
  • 4+ years of experience as a Data Scientist or Machine Learning Engineer applying ML in high-traffic production environments.
  • Production experience with deep learning ranking architectures including DCN-V2, MMoE, and Two-Tower; multi-task learning, cross-feature interactions, embedding optimization at scale, LTR methods, NDCG, MRR, and connecting offline metrics to online A/B outcomes.
  • Proficiency with LLM coding agents and agentic CLI tools for autonomous experiment generation, architecture prototyping, and rapid iteration; familiarity with auto-research and reviewing large volumes of generated results.
  • Expert Python across PyTorch, TensorFlow, and scikit-learn; working knowledge of SQL and dbt; experience with GCP or AWS and big-data processing using PySpark or Scala.
  • Hands-on MLOps experience across the full lifecycle, including feature stores, vector databases, model registries, Metaflow, ML CI/CD, experiment tracking, A/B frameworks, low-latency deployment, and production monitoring.
  • Track record of leading data science projects in ambiguous, complex problem spaces with long-term product or architecture impact.
  • Experience setting technical standards across multiple teams, building stakeholder consensus, and explaining model trade-offs to technical and non-technical audiences.

Culture & Benefits

  • Hybrid working model with two days per week in the Berlin campus.
  • 27 days of holiday, with an additional day in the second and third years of service.
  • €1,000 educational budget, language courses, parental support, and Udemy Business access.
  • Health checkups, meditation and gym support, life and accident insurance, corporate pension plan, and public transportation discounts.
  • Employee Share Purchase Plan, Sabbatical Bank, digital meal vouchers, and food vouchers.
  • Relocation support for moving to Berlin.

Hiring process

  • Apply through hirify.global’s hiring process and prepare for the interview using the provided interview guidance.
  • Accessibility support can be requested during the interview process.

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 →