Lead Machine Learning Engineer (Personalization & AI Models)

We are seeking a Lead Machine Learning Engineer (Personalization & AI Models) to pioneer the building and optimization of user segmentation, recommendation, and embedding models within our expansive personalization system for a Mobile App. The focus areas will include multi-vector representations, real-time model inference, and the integration of personalization workflows with cutting-edge technologies including AWS Personalize SDK, PGVector, and Rudder.

Stack.

Responsibilities

Develop and optimize embedding models using sentence-transformer models for user profiles and personalization Implement KNN-based recommendation systems for real-time content scoring and ranking Utilize AWS Personalize SDK to train and deploy machine learning models that dynamically adapt to user behavior Integrate embedding models with Databricks, Rudder.

Stack, and AWS services to ensure real-time profile updates Fine-tune ML models aimed at boosting revenue predictions, enhancing user engagement, and refining audience segmentation Optimize PGVector and Redis for efficient vector-based lookups and caching Collaborate with data engineers to devise ML pipelines for robust training, validation, and deployment processes Requirements Strong experience in Machine Learning, Deep Learning, and AI-driven personalization Proficiency in Python, Py.

Torch, and Tensor. Flow Expertise in vector-based search and recommendation systems, including knowledge of KNN, PGVector, Redis Hands-on experience with AWS Personalize SDK and Sage. Maker or similar ML training pipelines Familiarity with Databricks, Delta Lake, and Apache Spark for large-scale model training and deployment Strong understanding of real-time personalization, A/B testing, and user segmentation models Capability to work with event-driven architectures and implement real-time feature engineering Fluent English communication skills at a B2+ level Nice to have Knowledge of ML model monitoring, MLOps, and automation of ML pipelines through CI/CD Experience with Graph Neural Networks (GNNs) for analyzing user similarity and clustering Familiarity with deployment of real-time analytics tools and dashboarding, such as Looker, Tableau, or Snowflake