Software Engineer II

Microsoft Microsoft · Big Tech · Bengaluru, KA, IN +1 · Software Engineering

Software Engineer II at Microsoft to build and operate cloud services for large-scale AI model inference. The role involves designing and delivering backend services for high-volume, asynchronous AI workloads, intelligent traffic direction, distributed systems, large-scale scheduling, capacity optimization, and service reliability at hyperscale.

What you'd actually do

  1. Design, build, and operate scalable, reliable backend services that process high-volume, asynchronous AI inference workloads.
  2. Develop intelligent scheduling and request-routing capabilities that make efficient, load-aware use of available compute capacity.
  3. Improve throughput, latency, and cost efficiency of large-scale workloads through profiling, tuning, and thoughtful system design.
  4. Instrument services with strong telemetry, monitoring, and alerting, and participate in on-call rotations to ensure high availability.
  5. Partner with product and platform teams to onboard new models and capabilities and to support growing enterprise adoption.

Skills

Required

  • designing and building backend or distributed services
  • modern programming language such as C#, Java, Go, or C++
  • building and operating services on a public cloud platform such as Azure, AWS, or GCP

Nice to have

  • large-scale distributed systems
  • high-throughput data processing
  • asynchronous/batch workloads
  • scheduling, queueing, load balancing, or request-routing systems
  • observability tooling
  • operating production services in an on-call model
  • containerized services and orchestration (e.g., Docker and Kubernetes)

What the JD emphasized

  • high-volume, asynchronous AI inference workloads
  • large-scale scheduling
  • capacity and throughput optimization
  • service reliability
  • hyperscale

Other signals

  • large-scale AI model inference
  • cloud services
  • distributed systems
  • capacity and performance
  • hyperscale