12 часов назад
Team Lead ML (RecSys)
- Удалённо
PythonMLA/B testingPyTorchDeep LearningNLPRecSysTrust & Safety
Описание
Responsibilities
- Lead the recommendation system and other ML projects for the product.
- Be responsible for RecSys end-to-end: candidate generation, ranking, re-ranking, cold start, and exploration for a two-sided dating product.
- Define goals and metrics, monitor quality and drift, perform rollbacks and analyze degradations.
- Conduct A/B experiments with a product analyst.
- Areas of responsibility also include Trust & Safety, anti-fraud, moderation, liveness, monetization, retention, and chat NLP.
- Build a team and processes.
- Interact with the data platform and analytics.
- Participate in the design of key models and critical pipelines, and code reviews.
Requirements
- Experience with recommendation systems in production and responsibility for their online results.
- Practical experience with deep learning, PyTorch or equivalents, neural network ranking and retrieval, two-tower, sequence, and multi-task models, big data, and inference optimization.
- Knowledge of modern NLP models, transformers, embeddings, and fine-tuning.
- Experience in classification and ranking of user texts.
- Proficiency in classical ML, CatBoost or LightGBM.
- Confident Python skills.
- Ability to deploy models to production.
- Understanding the differences between offline metrics and online effect, biases, feedback, and drift.
- Skills in monitoring, reproducibility, versioning, and data testing.
Nice to have
- Leadership experience, hiring and developing specialists.
- Online experiments in recommendations.
- Reciprocal recommendations and two-sided markets.
- Trust & Safety, anti-fraud.
- Computer vision, uplift, churn, bandits.
- ClickHouse, Airflow, vector search.
- Publications, reports, and mentorship.
We offer
- Employment under the Labor Code of the Russian Federation.