Staff Software Engineer, ML Infra & Distributed Systems

Role overview

Build and evolve the distributed infrastructure that lets machine-learning teams serve models with low latency and high throughput. The platform supports applications such as recommendations, search, and content understanding, and includes reusable serving components, feature and vector stores, and experimentation capabilities. The role combines hands-on system design with technical leadership across engineering and product teams.

Responsibilities - Design and build scalable distributed services for high-throughput, low-latency ML inference. - Develop reusable infrastructure for applications including personalization, search, advertising, and exploration. - Work with ML engineers to identify platform constraints and shape practical, scalable solutions. - Use operational data to improve latency, cost, and efficiency, and lead broader refactoring when needed. - Help define the long-term architecture for ML infrastructure with product and engineering partners. - Mentor engineers in system design, incident response, interviewing, and effective use of AI coding tools.

Requirements - Experience designing and operating distributed systems in a modern backend language; Scala or another JVM language is useful. - Strong experience with AWS or a comparable cloud platform and large-scale, low-latency online services. - Familiarity with SQL and NoSQL databases, message brokers, and caching systems. - Experience with containers, such as Docker or Kubernetes. - Experience leading the response and resolution of multiple major production incidents.

Nice to have

Experience with inference engines, vector or feature stores, model-training orchestration, or ML serving systems is useful. Background in recommender systems, search, autocomplete, advertising ML, or analysis of A/B test results is also relevant. Experience with Akka, Erlang, Elixir, or Go is a plus.

Benefits and work setup

The position is described as hybrid. It is eligible for an annual discretionary bonus, long-term incentives, and benefits including health, dental and vision coverage, insurance, retirement savings, and paid time off. Salaried employees have flexible time off; eligible full-time employees receive 12 weeks of paid parental bonding leave and a monthly wellness reimbursement. The listed annual pay range for high-cost U.S. labor markets is $227,200–$324,500; final compensation depends on location, education, skills, and experience.