обновлено 4 дня назад
Machine Learning Engineer (Personalization)
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
Текст:
TL;DR
Machine Learning Engineer (Personalization) (Recommender Systems, Causal ML): Building production models for recommendations, personalized offers, churn prediction, and lifecycle interventions with an accent on incrementality, multimodal content understanding, and measurable business impact. Focus on designing holdout experiments, preventing leakage and bias, serving models on live traffic, and optimizing revenue, retention, margin, and abuse constraints.
Location: Almaty, Kazakhstan; fully on-site in the Almaty office five days per week for the full working day.
Salary: Competitive base salary in USD, based on experience, skills, and role scope.
Company
builds generative AI tools for video creation and next-generation creative experiences, serving millions of users and major global brands.
What you will do
- Build recommendation and ranking systems for effects, presets, templates, models, prompts, and post-generation experiences.
- Develop uplift models for discounts, vouchers, trials, upgrades, and win-back campaigns, supported by randomized holdouts and permanent experiments.
- Build churn, downgrade, and repeat-purchase propensity models and connect every model to an intervention and experiment.
- Create multimodal features and intent taxonomies from prompts, images, videos, outputs, model parameters, and generation outcomes.
- Own models end to end, including problem framing, feature engineering, training, offline evaluation, serving, monitoring, retraining, and production experimentation.
- Track model value in revenue, retention, margin, and abuse constraints while collaborating with Legal on personalization requirements.
Requirements
- Experience shipping machine learning models to live user traffic and changing business metrics.
- Depth in at least two areas: recommender systems, learning-to-rank, uplift and causal machine learning, churn or propensity modeling, or real-time personalization.
- Strong causal literacy, including randomized holdouts, incrementality, Qini/uplift evaluation, and selection effects.
- Strong Python and SQL skills, with experience in gradient boosting, neural ranking, feature pipelines, training-serving skew, latency budgets, and retraining.
- Product judgment, pragmatic delivery, and the ability to define the decision and metric before selecting a model.
- Clear written and spoken English at B2+ level; willingness to work on-site in Almaty five days per week.
Nice to have
- Experience working with images and video as data.
- Background in consumer-scale recommender systems, growth or monetization ML, causal inference, uplift modeling, or applied science.
- Experience in subscription products, gaming, fintech, or e-commerce.
Culture & Benefits
- Equity participation through the company’s stock option program.
- Relocation support to Almaty for candidates moving from another city or country.
- Company-provided equipment, meals, transportation, and other office benefits.
- Opportunities for professional growth, ownership, and career development.
- Collaborative, fast-paced in-person environment with direct access to experienced leaders.
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 →