kalyan dahake

I am an MLOps and AI Infrastructure Engineer with 3+ years building secure, compliant, cloud-native ML pipelines and deployments for high-reliability environments, including financial-grade applications.

I have designed and implemented automated MLOps pipelines using MLflow, CI/CD, and model versioning to enable audit-ready, governed deployments, and engineered Agentic LLMOps and RAG systems with Python and AWS Bedrock for document auditing workflows.

My cloud and Kubernetes work includes provisioning AWS ML infrastructure with Terraform, hardening clusters (RBAC, PodSecurity, Trivy, Kube-bench), and scaling inference on EKS with Docker and HPA to improve reliability and reduce deployment overhead.

I build production model serving and observability stacks—FastAPI/MLflow servers, Prometheus and Grafana dashboards—for latency, drift and API health monitoring, and I hold an AWS Machine Learning Specialty certification.