Staff/Senior Software Engineer
On-site · United StatesVisa sponsorship offered
Core
Fit a fleet of models into a fixed GPU budget and keep them fast for 10M users.
Role type
Staff/Senior Software Engineer (AI Infrastructure)
Builds
Serving infrastructure for a social AI platform
Domain
AI / Machine Learning Infrastructure
Deliverable
production ML models
Required skills
GPU resource management, latency optimization, cost per token optimization, infrastructure ownership, system design
Preferred skills
High ownership, ability to define problems and plans, comfort with ambiguity
Technologies
GPU clusters, model serving frameworks
Responsibilities
Optimize model serving latency and cost per token, manage GPU budget allocation, decide on infrastructure rebuilds and capacity scaling
Seniority
Senior, hands-on IC
