Machine Learning Engineer 3

About the role

In this position, you will build and develop machine learning models from scratch, including custom transformer-based frameworks, to identify fraudulent actions, stop account sharing, and protect the experience of hundreds of millions of users. You will manage the entire model lifecycle: raw behavioral data and feature engineering, architecture development, large-scale GPU training, deployment, and monitoring.

What you'll do

• Build and train deep learning models from scratch, including custom transformer and attention-based architectures for long behavioral event sequences
• Own the full training stack: event tokenization, temporal and positional embeddings, self-supervised pretraining (e.g., masked modeling, contrastive learning)
• Train large models efficiently on GPU infrastructure using mixed-precision training, gradient accumulation/checkpointing, efficient attention
• Build and optimize feature pipelines on Databricks and Spark, transforming raw behavioral events into high-quality model inputs
• Translate prototypes into production ML systems — scalable, reliable, and observable — and drive inference performance through architectural and serving-side optimization

What you need

• 5–9 years in data science & ai
• Machine learning
• Python
• PyTorch
• TensorFlow
• Deep learning
• MLOps
• B.Tech or B.E. or B.Sc or BCA or M.Tech or MCA or M.Sc

Good to have

• Databricks
• Spark
• CI/CD
• Prototyping