Principal Software Engineer, AI Infrastructure
Core
Design and manage AI traffic routing, computing capacity, and infrastructure reliability across global regions.
Role type
Principal Software Engineer (AI Infrastructure)
Builds
Distributed AI services, traffic routing systems, and GPU fleet management platforms.
Domain
Cloud Infrastructure / AI Systems
Deliverable
production ML models
Required skills
Distributed systems design, Traffic routing and scheduling, Resource optimization, Python, Docker, Kubernetes, AI/ML infrastructure, GPU fleet management, System reliability engineering, Threat modeling, Mentorship
Preferred skills
C#, Java, Go, Responsible AI practices, AI tooling in SDLC
Responsibilities
Design overall architecture for AI traffic and capacity management, Write and review secure code for routing and capacity planning, Partner with product teams to execute long-term roadmaps, Lead on-call rotation and incident post-mortems for critical AI services, Collaborate with cross-functional teams to prepare for model launches, Mentor engineers on building reliable systems at scale
Seniority
Principal, hands-on IC with strategic design and mentorship
