CAI Stack provides modular AI infrastructure for enterprises to build, scale, and deploy advanced ML and DL solutions. Our platform enables organizations to create vertical-specific AI applications that deliver personalized and actionable insights for users worldwide.

We are seeking a Senior Data Scientist to lead the development of deep learning-based recommender systems. The role requires hands-on expertise in designing scalable architectures, optimizing embeddings, and deploying production-grade models that enhance personalization and drive business impact.

Lead the full lifecycle of deep learning recommender systems, including research, design, development, and deployment.

Design multi-stage recommendation pipelines covering candidate generation and ranking with advanced architectures.

Develop and optimize models such as Two-Tower, Wide & Deep, session-based, and Transformer-based recommendation systems.

Manage large-scale embeddings for high-dimensional categorical data representing users and items.

Leverage specialized libraries and frameworks including TorchRec, TFRS, Microsoft Recommenders, Alibaba RecSys, and NVIDIA Merlin.

Address recommender system challenges such as cold-start and long-tail item recommendations.

Collaborate with cross-functional teams including data engineers, ML engineers, and product managers to deliver scalable and robust pipelines.

Design, implement, and analyze A/B tests to evaluate new models and features.

Apply MLOps best practices for production monitoring, continuous integration, and deployment.

Mentor junior team members and foster innovation in the recommendation space.

Advanced degree (M.S. or Ph.D.) in Computer Science, Statistics, or a related quantitative field.

Minimum 3 years of experience developing recommendation systems at scale.

Experience with big data platforms (Spark, HDFS, Databricks) and vector databases.

Knowledge of modern deep learning architectures for sequence modeling (e.g., Transformers).