About the Role
Join an early-stage AI company building personalized advertising and recommendation technology. You will own the matching system end to end, from model development through real-time serving, helping shape a core product capability.
What You'll Do
Build retrieval, ranking, and re-ranking systems to match ads with recipients.
Develop embedding and vector-search infrastructure for real-time ad selection.
Optimize ranking for click-through rate, advertiser return, publisher revenue, and subscriber relevance.
Own the feature store and serving path, including offline training, online inference, and consistency between them.
Apply large language models and foundation models to subscriber tagging, content understanding, and user modeling.
Take initiatives from prototype to production, including online learning, feedback systems, ETL/ELT pipelines, and warehouse transformations.
Create dashboards and scorecards to track system health and business and model performance.
Work with company leadership and engineering to set priorities, and help scale the recommendation system and future ML team.
What We're Looking For
Five or more years of relevant experience, including at least three years building recommendation, ranking, or advertising systems.
Experience shipping production recommendation or matching systems across candidate generation, ranking, embedding-based retrieval, serving, and evaluation.
Background building ad ranking, click-through or conversion prediction, or ad-matching models.
Hands-on experience with embeddings and real-time vector search, such as FAISS, Milvus, Pinecone, pgvector, or similar tools.
Strong SQL skills and experience building data pipelines and transformation layers with dbt or similar tools, plus Postgres or analytical databases.
Ability to work independently in an early-stage environment; startup or team-building experience is beneficial.
Must be authorized to work in the United States without visa sponsorship.
Compensation & Benefits
Base salary range: $200,000 to $300,000 annually. Visa sponsorship is not available.
Location
Hybrid work arrangement. Candidates should be based in the New York City area, or in a U.S. time zone near Eastern time and able to travel to New York City quarterly.