I work across data science, machine learning engineering, and scalable software systems, with particular depth in advertising, search, recommendation, causal measurement, and applied AI.
Contextual graphs, recommender systems, search science, advertising, marketing science, MMM, MTA, incremental lift, causal inference, propensity-score modeling, experimentation, predictive modeling, and statistical evaluation.
Embedding-based retrieval, two-tower models, information retrieval, NLP, transformers, LLM applications, anomaly detection, classification, ranking, and production-oriented model development.
Spark with Scala and PySpark, Flink, Hive, Airflow, EMR, Kafka, Athena, Redshift, Databricks, Delta Lake, DuckDB, streaming pipelines, ETL, monitoring, and production ML workflows.
Node.js, React, Flask, Spring, Play Framework, Akka, REST APIs, Docker, Kubernetes, CI/CD, model productization, distributed systems, data visualization, Amazon AWS, and Microsoft Azure.
Neo4j and graph databases; Firebase, HBase, Cassandra, MongoDB, and other NoSQL systems; PostgreSQL, Redshift, HiveQL, Microsoft SQL Server, Oracle, and MySQL.
AdTech and marketing science, affective computing, news mining, graph mining, anomaly detection, information retrieval, text mining, NLP, trustworthy AI, and empirical evaluation of applied AI systems.