Leading an awesome team of data scientists and software engineers focused on Indeed's ad products. If you've sponsored a job on Indeed you've used our systems. Areas of notable focus include the creation of targeting models for bidding, contextual and classic multi-armed for price optimization, supervised ML models for outcome estimation and a high-volume of experimentation focused on new product development and iteration.

Leading a full stack Data team of 50+ team members focused on Shopify's Shop App and Shop Pay. Areas of notable focus include core data engineering, search ranking, product recommenders, experimentation and high-level reporting.

Lead large, diverse and high-performing team of Data Scientists and Machine Learning engineers focused on the creation of models and systems to drive key product areas. Firm believer in collaboration across functions and presenting machine learning in approachable and interpretable terms.Specifically:- Reinforcement learning and whole page optimization- ML-driven personalization- Recommender systems- Price Optimization and demand estimation- ML-based caching and latency optimization - Search ranking and monetization- NLP- Content and page layout optimization- Computer vision: object detection, scene classification and quality scoring- Geospatial relevance and optimization of core geographic entities

Founding leader of search ranking data science team. Led team responsible for multiple large conversion winner A/B tests and complete overhaul of ranking system to be machine learning driven. Created relevance models, offline evaluation framework, specified built and launched experiments in partnership with DS team and engineering.

- Focused primarily on search relevance and ranking with significant time on geospatial relevance- Lead data scientist on next generation ML-based marketplace ranking system- Create Vrbo's first recommender system

- Text classification and regression problems- Taking said models to production via Python-based microservices running in AWS- Some graph-based semi-supervised learning using social media data- A bit of vanilla text processing and probably too much regex hacking

Streaming social media data processing with Storm, Java and Solr. Build machine learning models of Twitter sentiment, Twitter author gender and others. Ad hoc data analysis and visualization.