Description

You will design and implement machine learning models to improve the precision and recall of identity resolution algorithms. You will own the end-to-end lifecycle of scalable ML solutions in production, from feature engineering to deployment.

Responsibilities

• Design, implement, and refine ML models to enhance identity matching and unification.
• Develop and optimize feature engineering methodologies for large, complex datasets.
• Build and maintain scalable data infrastructure for efficient model training and deployment under varying loads.
• Train and validate deep learning and statistical models, balancing complexity, performance, and robustness.
• Partner with product managers and tech leads to analyze business problems and define system scope.

Required Skills

• 7+ years of applied machine learning experience.
• Proficiency in Python, Java, or Golang.
• Extensive experience in feature engineering and data-driven frameworks for identity matching.
• Strong background in machine learning foundations and modern deep learning building blocks.
• Experience with TensorFlow, PyTorch, or Scikit-learn.
• Familiarity with big data technologies such as Apache Spark, Hadoop, and cloud platforms (AWS, Azure, GCP).
• Experience with ML Ops concepts including testing, retraining, and monitoring models in production.
• Proficiency with modern data storage and processing tools: DynamoDB, Kafka, Presto.

Preferred Skills

• Exposure to Advertising Technology or Marketing Technology domains.
• Experience designing highly available, fault-tolerant distributed systems.

Key Skills

Education

Any Graduate