Skip to main content
Raunak Bele

Raunak Bele

Site Reliability Engineer with 4+ years of experience managing cloud-native applications on Azure and Kubernetes

Talent
MumbaiMember since September 28, 2026
PythonAzureTerraformKubernetesHelmNVIDIA GPU SchedulingMIGAir-Gapped Kubernetes DeploymentsGitHub ActionsPrometheusGrafana
·

Hire this person

Send a job offer directly to this candidate

PythonAzureTerraformKubernetesHelm

About

Site Reliability Engineer with 4+ years of experience managing cloud-native applications on Azure and Kubernetes. Skilled in observability, incident management, Terraform automation, and GPU-accelerated AI/ML infrastructure. Hands-on experience deploying LLM/SLM workloads using NVIDIA GPUs, MIG partitioning, autoscaling, and airgapped Kubernetes environments. Proficient in Python, CI/CD, and production troubleshooting, with proven impact in reducing MTTR and optimizing infrastructure efficiency.

Experience

Site Reliability Engineer II at ANDOR TECH INDIA PRIVATE LIMITED (2026-04 – Present)

  • Managed air-gapped Kubernetes deployments enabling secure model serving for enterprise environments
  • Explored NVIDIA GPU scheduling, including MIG configurations, for optimized inference workloads
  • Collaborated on Kubernetes pod resource optimization for CPU, memory, and GPU utilization
  • Deployed scalable Llama and Mistral models reducing inference response latency by 25% overall
  • Participated in air-gapped deployment discussions following enterprise container security best practices

Site Reliability Engineer II at HONEYWELL TECHNOLOGY SOLUTIONS LAB PRIVATE LIMITED (2025-01 – 2026-03)

  • Reduced MTTR by 25% through optimized log queries and alert improvements
  • Monitored performance using Prometheus, Grafana, Azure Monitor improving system reliability 20%
  • Built CI/CD pipelines using GitHub Actions enabling 40% faster builds deployments
  • Managed 20+ Kubernetes workloads using Helm ensuring scalable reliable deployment processes
  • Automated infrastructure provisioning using Terraform improving consistency 35% reducing environment drift

Performance, Scalability and Reliability Engineer I at HONEYWELL TECHNOLOGY SOLUTIONS LAB PRIVATE LIMITED (2022-08 – 2025-01)

  • Executed load, stress, endurance testing for 5+ services, validating 50+ concurrent users
  • Improved API latency by 35% and throughput by 25% via profiling and optimization
  • Partnered with agile teams across 30+ releases, ensuring zero critical production regressions

Intern Bachelors Software Engineer at HONEYWELL TECHNOLOGY SOLUTIONS LAB PRIVATE LIMITED (2022-01 – 2022-06)

  • Developed centralized alerts portal improving cross-environment operational visibility
  • Automated notifications using Python services reducing manual monitoring efforts

Education

B.Tech in CSE – Amrita School of Engineering (2018 – 2022)

Reviews

Related