Senior Applied ML Engineer, Search & Relevance

What you'll do

• Build and iterate on font discovery features from initial specification through production deployment.
• Manage search relevance and ranking using techniques like candidate generation, vector search, and learning-to-rank.
• Develop recommendation systems for related fonts, pairings, and contextual suggestions.
• Ensure production reliability by managing latency, scale, observability, and participating in on-call rotations.
• Design infrastructure for model features, low-latency serving, evaluation harnesses, and A/B testing.
• Define and defend success metrics to bridge the gap between offline relevance and online outcomes.
• Implement machine learning tools like embeddings and fine-tuning to improve search and recommendation results.

What we're looking for

• Must possess strong software engineering fundamentals including design, testing, code quality, and code review.
• Must demonstrate production maturity in managing latency, scale, reliability, and observability for services.
• Must have hands-on experience with embeddings, model fine-tuning, and retrieval systems like ANN or vector search.
• Must possess expertise in ranking techniques such as learning-to-rank and search optimization.
• Must have a solid understanding of recommendation systems and personalization at scale.
• Must be able to design evaluation harnesses, define metrics, and perform offline/online debugging.
• Experience with information retrieval internals like Elasticsearch, OpenSearch, or Solr is preferred.
• Knowledge of GenAI, LLM-assisted retrieval, or agentic workflows is preferred.