At Fetch, we are on a mission to build the most comprehensive product catalog across every retailer in the U.S., and eventually the world. Our catalog is the backbone of the Fetch platform, powering critical features such as personalization, relevance, search, and product matching. This catalog doesn't just track basic product information; it includes rich metadata like category taxonomies,  images, and purchase history data to fuel our advertising capabilities and enhance the overall user experience.

We are seeking a Staff Software Engineer with deep expertise in building and scaling large, data-rich product catalogs. This role is crucial to leveling up our catalog and data capabilities, which will drive many of Fetch’s most important future initiatives. The ideal candidate has a blend of technical proficiency, domain knowledge, and experience in areas like data ingestion, machine learning, and potentially AdTech.

Responsibilities:

• Collaborate closely with cross-functional teams, including engineers, data analysts, product managers, and ML specialists, to build a comprehensive and scalable product catalog.
• Lead the design, implementation, and optimization of critical components of the catalog, such as product ingestion pipelines, data enrichment, metadata generation, and data serving infrastructure.
• Ensure the catalog serves as the foundation for personalization, relevance, search, and product matching across Fetch’s app, while supporting additional use cases like image-based ad generation and real-time product recommendations.
• Develop robust solutions to ingest product data from multiple sources (partners, third-party data providers, and web scraping) and harmonize that data to maintain a unified, up-to-date product catalog.
• Collaborate with the ML team to integrate state-of-the-art machine learning techniques for data classification, entity resolution, and content enrichment (text, images, etc.).
• Mentor team members, fostering a culture of knowledge sharing and technical excellence.

In your toolbag (Minimum requirements):

• 5+ years of experience building and maintaining large-scale, high-performance product catalogs or similar data-driven applications, with a strong focus on reliability, scalability, and accuracy.
• Proven experience delivering software in a high-traffic production environment, with an emphasis on data quality, integrity, and operational excellence.
• Strong proficiency in at least one of the following programming languages: Python, Go, Java, with the ability to write clean, efficient, and maintainable code.
• Expertise in cloud-based distributed systems (AWS or similar), microservices architecture, and handling large-scale data ingestion and processing workflows.
• Familiarity with machine learning techniques for data cleaning, enrichment, and classification tasks, such as entity resolution, named entity recognition, and image/text classification.
• Strong understanding of data modeling and data structures, especially in building product catalogs with complex relationships between entities.

Nice to Have:

• Experience with AdTech or systems that optimize and generate ad content using product metadata.
• Experience using GenAI/LLMs to automate data cleaning, enrichment, and categorization tasks.
• Knowledge of search system optimization and experience building or enhancing relevance and ranking algorithms.
• Familiarity with taxonomy design, knowledge graph construction, or other advanced data modeling techniques to structure and enrich the catalog.
• Experience with web scraping and data aggregation from diverse external sources to support catalog growth and data coverage.