Principal Software Engineer
Core
Design, implement, and operate cloud-scale services to improve GPU inference efficiency, utilization, and cost across Azure.
Role type
Principal Software Engineer (GPU Inference Infrastructure)
Builds
Production-ready infrastructure for GPU inference, telemetry, experimentation, and control-plane capabilities
Domain
Cloud infrastructure, distributed systems, GPU computing, AI/ML inference
Deliverable
production ML models | infrastructure
Required skills
GPU infrastructure development, distributed systems design, inference-serving system optimization, workload scheduling, capacity management, performance engineering, system reliability, security practices, technical strategy, architecture design, mentorship
Preferred skills
None stated
Technologies
C#, Rust, Python, C++, C, Java, JavaScript
Responsibilities
Design and implement cloud-scale services for GPU inference efficiency; Build telemetry and control-plane capabilities for fleet-scale validation; Drive architecture and technical strategy for workload placement and capacity management; Mentor engineers and lead technical reviews; Collaborate across hardware, platform, and AI teams to land cross-organizational initiatives
Seniority
Principal, hands-on IC with strategy & mentorship
