About the Role
You will build and maintain user-facing, latency-sensitive inference APIs. You will design APIs, create multi-cloud inference infrastructure, define scalable billing and business-logic abstractions, expose model features, and improve backend reliability and on-call operations.
Requirements
•5+ years of professional software engineering experience
•3+ years of infrastructure or backend experience
•Experience designing storage abstractions for scaled backend systems
•Experience designing resilient production systems
•Experience shipping backend services at scale with continuous delivery and uptime SLAs of at least 99.9%
•Experience designing and operating developer-facing API services
•Experience implementing LLMs and understanding their capabilities and limitations
Responsibilities
•Define and iterate on APIs for AI inference
•Create infrastructure for serving inference across multiple cloud providers
•Define abstractions for billing and business logic
•Expose new model features to users
•Design storage abstractions for scaled backend systems
•Design resilient production systems and improve on-call experience
•Collaborate on technical and product design
Benefits
•Equity
•100% covered health insurance
•Daily lunch and dinner
•Visa sponsorships
•401K plans
