Senior Applied ML Engineer, Search & Relevance

What you'll do

• Build and ship end-to-end font-discovery experiences from initial specification to production.
• Own search relevance and ranking including candidate generation, retrieval, and learning-to-rank.
• Develop and improve recommendation surfaces for related fonts and contextual suggestions.
• Manage production service health including latency, scale, reliability, and observability.
• Design systems for feature pipelines, low-latency serving, and evaluation harnesses.
• Define and defend offline and online metrics while debugging gaps between them.
• Apply machine learning techniques like embeddings and fine-tuning to improve discovery.

What we're looking for

• Demonstrate strong software engineering fundamentals including design, testing, code quality, and code review.
• Possess system design and production maturity regarding latency, scale, reliability, observability, and on-call support.
• Ship and own services end-to-end with a pragmatic approach to build-vs-buy tradeoffs.
• Maintain a working understanding of embeddings, models, fine-tuning, retrieval, and ranking (ANN / vector search, learning-to-rank).
• Apply ML judgment to search optimization, recommendation systems, and relevance optimization.
• Design evaluation harnesses, metrics, and debug gaps between offline and online outcomes using behavioral data.
• Experience with personalization at scale, feature stores, or model serving infra (preferred).
• Knowledge of information retrieval internals, hybrid search, or GenAI/LLM-assisted retrieval (preferred).