Назад
Company hidden
2 часа назад

Senior Data Scientist (Personalization)

175 000 - 190 000$
Формат работы
remote (только USA)/hybrid
Тип работы
fulltime
Грейд
senior
Английский
b2
Страна
US
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 Data Scientist (Personalization): Building and improving recommendation models that power personalized product feeds from user signals and large retail catalogs with an accent on embeddings, retrieval, cold-start personalization, and rigorous experimentation. Focus on designing full-cycle machine learning solutions, extracting product attributes with NLP and computer vision, and deploying models through the existing MLOps stack.

Location: New York, NY, with remote work available within the United States; employees within commuting distance of New York offices are expected to work onsite three days per week.

Salary: $175,000–$190,000 annually in New York; $160,000–$175,000 annually for Remote US.

Company

hirify.global operates a product discovery platform that connects shoppers with products from thousands of retail partners through personalized recommendations.

What you will do

  • Design, train, evaluate, and improve recommendation and personalization models for individualized product feeds.
  • Build user and product embeddings, candidate-generation systems, and vector retrieval solutions across a catalog scaling toward tens of millions of products.
  • Develop cold-start strategies for new users and products with sparse behavioral data.
  • Design and analyze offline evaluations, A/B tests, and multivariate experiments to connect model quality with product and business outcomes.
  • Use SQL, BigQuery, NLP, computer vision, and LLM-based techniques to transform behavioral and catalog data into model features.
  • Deploy and monitor production models through the existing MLOps stack and collaborate with MLOps, engineering, and product teams.

Requirements

  • Master's degree or higher in computer science, statistics, machine learning, applied mathematics, or a related quantitative field, or equivalent practical experience.
  • Strong foundations in data science, statistics, experimental design, ranking evaluation, and the full A/B testing lifecycle.
  • Experience designing, training, and deploying embedding models and vector retrieval systems at catalog scale.
  • Experience with cold-start or sparse-signal personalization for new users, new products, or both.
  • Strong Python, modern machine learning frameworks, pandas, NumPy, scikit-learn, and SQL; BigQuery experience is preferred.
  • Experience deploying and serving models on cloud ML platforms, with GCP Vertex AI strongly preferred, plus strong communication skills and commerce or product-catalog intuition.

Nice to have

  • Applied NLP or computer vision for extracting structured attributes from product text and imagery.
  • Experience with adaptive recommendation methods, multi-armed bandits, or contextual bandits.
  • Public writing or conference talks on recommendation, personalization, or ranking.
  • Early-stage company or commerce experience, including commerce SaaS or vertical commerce startups.

Culture & Benefits

  • Remote work flexibility within the United States, with a hybrid NYC schedule for employees who live nearby.
  • Medical, dental, vision, prescription drug, health savings, and flexible spending benefits.
  • Unlimited paid time off, paid holidays, paid parental leave, disability coverage, and family care benefits.
  • 401(k) savings plan with company match, tuition reimbursement, donation matching, and commuter benefits.
  • Additional benefits include life insurance, accident coverage, pet insurance, and adoption or surrogate assistance.

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 →