tldr: Sber, Deep Learning Intern (RecSys for Anti-Fraud), 81k RUB/month

👨‍💻 We are building models against fraud that work in real-time under high load, join us!

🎯 Task: adapt SASRec/HSTU/two-tower models for anti-fraud. Input: transaction chain + client profile, predict the last transaction.

🛠 Requirements: • solid Python, PyTorch (built models from scratch); • knowledge of architectures: Transformer, YouTubeDNN, SASRec, Bert4Rec, HSTU, ARGUS - at least a couple; • ability to work with tabular features for DL; • understanding of Negative sampling strategies and loss functions for ranking/classification tasks.

➕ Pluses: RecSys course with DL, experimented with various transformers, interest in anti-fraud and BigData.

💼 Conditions: paid internship 3–6 months, salary 81 thousand RUB, employment from 20 hours/week, SberCity office.

📩 Apply: shalamaeva In the message: about yourself, experience in PyTorch/RecSys, GitHub (if available).

Catching fraudsters together 🧑‍💻