Senior Software Engineer - AI Infrastructure
Core
Design and implement scalable distributed systems for Azure AI traffic management, routing, and workload optimization.
Role type
Senior IC software engineer (AI infrastructure)
Builds
Routing, capacity allocation, and workload optimization services for global AI infrastructure
Domain
Cloud infrastructure + AI/ML systems
Deliverable
production ML models
Required skills
Distributed systems, algorithm design, control-plane systems, observability, production issue investigation, platform automation, fleet efficiency optimization, engineering mentorship, long-term strategy planning
Preferred skills
Telemetry and metrics pipelines, resource scheduling systems, cloud platforms (Azure, AWS, GCP), container orchestration (Kubernetes, Service Fabric), large-scale service operations, distributed storage systems, real-time data processing, AI/ML infrastructure, GPU fleets, inference serving systems
Technologies
C, C++, C#, Java, JavaScript, Python, Azure, AWS, GCP, Kubernetes, Service Fabric
Responsibilities
Drive architecture and technical direction for routing and capacity allocation services; Develop algorithms to distribute AI workloads globally; Collaborate with partners to onboard new models and regions; Build observability tooling for service health and traffic monitoring; Lead investigations into complex production issues; Mentor engineers and review designs; Influence long-term platform strategy and roadmap planning
Seniority
Senior, hands-on IC
