Infra Engineer - API

Responsibilities

• Own the end-to-end production API for frontier research models
• Design and operate the video streaming protocol and request routing layer
• Manage GPU session lifecycle, inference orchestration, and runtime reliability
• Scale Kubernetes deployments across regions and support new regional launches
• Improve latency, throughput, observability, metering, and billing-grade uptime
• Partner closely with product engineering and the founding team on API evolution

Requirements

• Experience scaling high-traffic, low-latency APIs in production
• Deep Kubernetes experience, including multi-region deployments
• Strong understanding of capacity planning and SLOs
• Proven ownership of systems end to end
• Ability to work onsite in New York City

Preferred Qualifications

• Experience with streaming video or audio inference systems
• Background in low-latency game streaming or video streaming infrastructure
• Experience scaling GPU fleets across providers
• Familiarity with frontier model inference, multimodal systems, or edge inference

Benefits

• Competitive salary and meaningful equity
• Comprehensive medical, dental, and vision coverage
• 401(k) and paid parental leave
• Generous PTO, paid holidays, and paid sick time
• Daily meals, commuter benefits, and wellness support
• Learning and development stipend

About the Company

General Intuition is a frontier research lab building foundation models for spatial and temporal reasoning, including agents, world models, and video understanding systems. The team is backed by General Catalyst and Khosla and is focused on bringing frontier research into production.