Site Reliability Engineering 2

Microsoft Microsoft · Big Tech · Hyderabad, TS, IN +2 · Site Reliability Engineering

Site Reliability Engineering role focused on building and maintaining Kaibot, an AI-powered assistant for the Kusto platform. This involves designing, building, and improving AI-generated responses, partnering with other teams, and contributing to the operational health of the service. The role requires grounding LLMs in real data and ensuring reliability and safety of AI responses.

What you'd actually do

  1. Design, build, and maintain features for Kaibot, our AI-powered assistant for the Kusto (Azure Data Explorer) platform, delivered through Microsoft Teams and related surfaces.
  2. Partner with service engineering, support, and product teams to identify high-value engineer and customer scenarios and turn them into reliable self-service experiences.
  3. Improve the quality, reliability, and safety of AI-generated responses through evaluation, monitoring, and continuous feedback loops.
  4. Contribute to the operational health of the service — telemetry, alerting, and live-site readiness — and help the team continuously improve its engineering practices.
  5. Write clear, well-tested, maintainable code and collaborate through design discussions and code reviews.

Skills

Required

  • Bachelor’s Degree in Computer Science, or related technical discipline
  • 4+ years of technical engineering experience with coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, or Python or equivalent experience
  • Ability to meet Microsoft, customer and/or government security screening requirements

Nice to have

  • Experience building AI- or large-language-model-powered applications
  • retrieval-augmented generation (RAG)
  • prompt engineering
  • grounding
  • evaluation of model outputs
  • Experience developing and operating cloud services on Microsoft Azure
  • Familiarity with Kusto / Azure Data Explorer, Kusto Query Language (KQL), or other large-scale data and analytics platforms
  • Experience building conversational, bot, or Copilot experiences
  • Experience with service reliability practices — telemetry, monitoring, and live-site / on-call operations
  • Proficient collaborator, comfortable working across engineering, product, and support teams

What the JD emphasized

  • AI-powered assistant
  • ground large language models
  • trustworthy, actionable help
  • AI-generated responses
  • evaluation, monitoring, and continuous feedback loops
  • telemetry, alerting, and live-site readiness

Other signals

  • AI-powered assistant
  • ground large language models in real Kusto telemetry
  • trustworthy, actionable help at Microsoft scale