Senior Software Engineering - Azure Monitor

Microsoft Microsoft · Big Tech · IL, Herzliya, Tel Aviv District, IL · Software Engineering

Senior Software Engineer role focused on building and evolving core agents for Azure Monitor's Copilot Observability, involving LLM and agent orchestration, tool use, grounding, retrieval, evaluation, and system reliability at massive scale within enterprise-grade constraints.

What you'd actually do

  1. Architect, design, and build high-performance agents covering LLM and agent orchestration, tool use, grounding and retrieval, evaluation and system reliability, safety, latency and cost.
  2. Lead complex features and technical initiatives throughout their full lifecycle, from requirements and architecture through implementation, testing, deployment, and production operations.
  3. Solve challenging engineering problems involving massive scale, reliability, performance, resource efficiency, security, and fault tolerance.
  4. Drive technical direction and make sound architectural decisions that balance immediate requirements with long-term maintainability and evolution.
  5. Establish and promote high-quality engineering practices, including effective design reviews, testing strategies, operational readiness, and production diagnostics.

Skills

Required

  • 7+ years of hands-on software engineering experience
  • significant experience building and operating large-scale production systems
  • BSc or MSc in Computer Science, Software Engineering, or a related technical field, or equivalent practical experience
  • Proven ability to design and deliver complex, reliable, maintainable, and high-performance software systems

Nice to have

  • cloud-native platforms
  • distributed systems
  • modern microservice architectures
  • observability
  • telemetry pipelines
  • agents
  • SDKs
  • system-level programming
  • optimizing software for performance, memory, CPU, network usage, or other constrained environments
  • C#/.NET
  • Kubernetes/AKS
  • Kusto/ADX
  • developing services or components for Microsoft Azure or another large-scale cloud platform
  • security, privacy, and compliance requirements in enterprise software
  • building and evaluating LLM-based agentic systems
  • leading substantial technical projects or features across multiple development stages and stakeholders
  • Demonstrated ownership of production systems, including reliability, monitoring, troubleshooting, and operational excellence
  • High attention to detail
  • strong commitment to engineering quality

What the JD emphasized

  • massive scale
  • high scale
  • enterprise-grade requirements
  • complex technical initiatives
  • complex features
  • challenging engineering problems
  • sound architectural decisions
  • high-quality engineering practices
  • critical components end-to-end
  • timely delivery of robust, production-ready solutions
  • building and evaluating LLM-based agentic systems
  • leading substantial technical projects or features
  • Demonstrated ownership of production systems

Other signals

  • AI-powered systems
  • LLM and agent orchestration
  • tool use
  • grounding and retrieval
  • evaluation and system reliability
  • safety, latency and cost