Senior Staff Software Engineer, Search & Recommendation
Cantina · United States
About this role
## About Cantina Cantina Labs is a social AI company building advanced real-time models that expand expression, personality, and realism. We bring characters to life and transform how people tell stories, connect, and create—building and powering ecosystems. Cantina, our flagship social AI platform, is just the beginning. ## About the Role Cantina is a place where people create AI characters and the videos those characters star in. But the catalog grows faster than anyone can browse—so **Search & Recommendations** are what turn it into a product. You’ll help decide which characters a new user meets in their first minute, which creators get discovered, and what appears across every feed, leaderboard, and discovery surface. We’re hiring a **Senior Staff Software Engineer** to own Search & Recommendations end to end—**retrieval, ranking, relevance quality, and the roadmap for all three**. This is the first dedicated hire for this area, so you’ll inherit a real production system serving live traffic and set the technical direction. ## What You’ll Do - Own the architecture and roadmap for search and recommendations end to end - Drive query understanding, retrieval, ranking, and the surfaces they feed: search, discovery, the home feed, and trending/creator leaderboards - Make relevance a measured discipline: define quality metrics per surface, build offline evaluation + golden-set tooling, and run online experiments for ranking changes - Design and evolve the ranking stack, including engagement signal pipelines, decay/freshness models, and the combination of index-time signals with live re-ranking - Own **OpenSearch in production**: index/mapping design, reindex + cutover safety, query performance, cost, and operational headroom - Build candidate generation and personalization for recommendation surfaces; partner with data/ML on feature pipelines and models - Partner with Product and Trust & Safety to define what “good” means per surface (quality gates, cold-start behavior, and what must never be recommended) - Set the engineering standard for the area: instrumentation, flag-gated rollouts, and runbooks so other teams can change ranking behavior safely - Serve as the technical point of contact for discovery across backend teams and mentor engineers ## What You’ll Bring - **10+ years** building production software with substantial depth in search, ranking, recommendations, or ML-driven relevance on a consumer-scale product - Hands-on production search engine expertise (OpenSearch/Elasticsearch/Lucene/Vespa or similar), including index/analyzer design and cluster operations - A rigorous approach to relevance measurement (offline evaluation, golden sets, A/B or interleaving frameworks) and the ability to explain metric movement - Fluency across the recommender stack (candidate generation, feature pipelines, embedding retrieval, re-ranking) and understanding of why offline wins can fail online - Strong distributed systems + backend fundamentals; production experience in **Go or a comparable systems language**; comfort with the data layer (SQL warehouses, streaming/batch pipelines) - Demonstrated ownership of an ambiguous area (you picked up something with no dedicated owner and drove outcomes) - Clear written communication and good judgment working with Product on tradeoffs between relevance, freshness, safety, and latency - Preferred: experience with AI-generated or rapidly growing content catalogs, severe cold-start conditions, or rankin
Listing freshness
CronJobs last confirmed this listing 1h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.