SAMEER BANCHHOR
INDIA • CLOUD ENGINE
--:-- --
--:-- --
SAMEER BANCHHOR
DevOps Engineer with 3 years of experience designing, automating, and managing cloud-native infrastructure & AI platforms. Specialized in Kubernetes, Infrastructure as Code, vLLM & GPU workloads, CI/CD automation, observability, and high-availability operations.
Production infrastructure architectures engineered for reliability, automation, and scale.
3 years of experience designing, automating, and scaling production cloud infrastructure and AI model serving.
Designing, automating, and managing production-grade cloud-native infrastructure on AWS. Built reliable, scalable, secure, and cost-efficient platforms enabling engineering teams to deploy multiple times daily.
Engineering AI infrastructure for LLM applications, GPU workloads, inference deployments, vector databases, and scalable containerized platforms.
Proven expertise in blueprinting distributed, fault-tolerant, and high-throughput architectures.
Experience real-time GitOps deployment pipelines, interactive terminal command execution, and live cloud infrastructure topology scaling.
Run interactive infrastructure commands directly in-browser or click quick presets below.
Simulate cluster size, GPU hardware acceleration, and multi-region specs for real-time AWS cost and throughput metrics.
resource "aws_eks_node_group" "gpu_pool" {
cluster_name = "ai-production-cluster"
node_group_name = "vllm-a100-nodes"
instance_types = ["p4d.24xlarge"]
desired_size = 4
}Production Kubernetes platforms, AI inference servers, GitOps pipelines, IaC automation, and observability stacks.
High-Availability production Kubernetes cluster engineered with Terraform IaC, AWS cloud services, Helm charts, and GitOps delivery.
Scalable AI model inference and GPU workload management platform powering open-source LLMs and vector search backends.
Declarative multi-environment continuous delivery platform enabling zero-downtime rollouts and automated rollbacks across clusters.
End-to-end cloud infrastructure automation provisioning VPC networking, compute, storage, databases, and IAM security models.
Full-stack metrics, logging, and alerting platform delivering real-time operational visibility across cloud microservices.
High-performance Go REST API & Analytics Engine serving 1M+ records with sub-15ms latency. Deployed on Google Cloud Run (voter.sameerbanchhor.com).
End-to-end VITS neural audio synthesis pipeline and model serving framework for Chhattisgarhi dialect (18M+ speakers).
Industry certifications, open-source contributions, technical writings, and active code repositories.