- Oversaw strategic initiatives impacting revenue and operational efficiency, including real-time ML infrastructure and data product development.- Developed "market 360" models for optimizing user segmentation and inventory visibility.- Created a pricing model that increased revenue by 4-5 figures per month through improved margin management.- Deployed a fine-tuned GenAI model to extract structured data from unstructured job descriptions, enabling real-time job publishing and reducing time-to-publish.- Transitioned to a machine learning-powered recommendation system, delivering personalized job notifications via push and SMS, boosting application rates and revenue growth.- Built predictive models that enhanced placement conversions, resulting in an increase of $65k - $75k per week.- Led the development of a graph-based recommendation algorithm, personalizing content for over 200,000 users and generating over $500,000 in monthly revenue.- Automated the publication process for 300 new job postings using OpenAI models to extract structured information from unstructured job descriptions.- Deployed various predictive models to support business decisions and optimize operational workflows.- Collaborated with the Business Intelligence team and managed a Data Engineer to develop a data warehouse for faster organizational insights.- Proposed and organized a company-wide hackathon focused on GenAI, featuring around 90 participants and leading to several project deployments.

- Managed the Machine Learning team to deliver a recommendation service that enhanced job recommendations across The Muse's platform and in weekly emails sent to over 500,000 users.- Oversaw the Data Engineering team supporting the business intelligence unit by expanding and maintaining the ETL pipeline.- Successfully developed a real-time data pipeline with the team and established dbt pipelines, enabling the BI team to create their own data transformation workflows.

- Designed, built, and productionized recommendation algorithms that provided job and article recommendations for millions of unique visitors each month.- Developed a content-based natural language processing algorithm and a filtering algorithm with Apache Spark MLlib.- Utilized Python with libraries such as pandas, scikit-learn, and NLTK for algorithm implementation.- Computed recommendations in the nightly ETL pipeline and uploaded results to the PostgreSQL database supporting the in-house recommendation service.

- As the sole machine learning engineer, architected and built job recommendation and candidate matching systems.- Developed a content-enhanced collaborative filter that integrated user behavior and job description information to recommend jobs to thousands of job seekers.- Replaced SVD factorization with alternating least squares for improved scalability in the collaborative filtering algorithm.- Applied common NLP techniques for the content-based component of the recommendation system.- Implemented the algorithm in Python using primarily scikit-learn packages.

- Built applicant sourcing and screening software using TensorFlow for Deep Learning NLP and scikit-learn for simpler NLP techniques.