Skip to content
View milind2's full-sized avatar
0 followers · 2 following

Block or report milind2

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
milind2/README.md

Hi, I'm Milind 👋

Infrastructure engineer with 12+ years of experience, including time at Amazon Web Services, now focused on the operational backbone behind large-scale AI/ML systems — Kubernetes, GPU orchestration, and the reliability tooling that keeps model-serving infrastructure observable, debuggable, and recoverable at scale.

  • ☁️ 12+ years in cloud infrastructure and DevOps/SRE, including AWS (Cloud Support Engineer, Technical Account Manager)
  • 🤖 AI infrastructure: GPU cluster management, Kubernetes operators for ML workloads, Slurm/batch orchestration
  • 🔧 Go, Python, Terraform, Kubernetes/EKS, AWS Batch
  • 🧭 Agentic AI: built an AI property assistant (chatbot) and automated content generation for PropX8.com using LangChain/LangGraph
  • 📌 Recent work:
    • PropX8.com — AI-backed real estate platform (Mumbai) with an AI property assistant and agent-driven automated blogging, built at SkywardTech
    • gpu-guardian-operator — Kubernetes operator for GPU node health (Xid/ECC errors, thermal throttling), zero external dependencies
    • terraform-aws-eks-gpu-nodepool — end-to-end Terraform stack for GPU workloads on EKS (VPC, cluster, spot/on-demand GPU node pool)
  • 📫 Reach me: milind2sisodiya@gmail.com

Pinned Loading

  1. terraform-aws-eks-gpu-nodepool terraform-aws-eks-gpu-nodepool Public

    "End-to-end Terraform stack for GPU workloads on EKS — VPC, cluster, and a spot/on-demand GPU node pool."

    HCL

  2. gpu-guardian-operator gpu-guardian-operator Public

    Kubernetes operator for GPU node health — cordons/drains nodes on Xid/ECC errors or thermal throttling, zero external dependencies.

    Go

  3. vllm-k8s-deploy vllm-k8s-deploy Public

    Helm chart for deploying vLLM on GPU Kubernetes — startup probes tuned for slow model loads, correct GPU scheduling, sized /dev/shm, and GPU-utilization/queue-depth autoscaling.

    Go Template