Lakshmi Kiranmayi Chelluboyina

About

Built a hackathon "Patient Summary Assistant" backend focused on healthcare workflows, combining RAG-based summarization with HIPAA-minded privacy controls (NER redaction + encryption). Demonstrated strong infra skills by deploying on Kubernetes with Helm/HPA and GitOps (ArgoCD), plus migrating from OpenAI to an on-prem Llama 3 stack (vLLM, quantization, shadow-mode testing) and adding real-time Kafka ingestion for patient vitals/anomaly alerts.

Experience

Education

Key Strengths

• Built HIPAA-oriented privacy controls using NER redaction and Fernet encryption/key management
• Designed and implemented RAG-based patient summarization with embeddings and cosine-similarity retrieval
• Strong Kubernetes operations: Helm templating, rightsizing pods, resource requests/limits, HPA with custom metrics, rolling updates for zero downtime
• Implemented automated CI/CD with GitHub + pytest, image build/tag/push, and deployment updates via kubectl
• Executed cloud-to-on-prem LLM migration (OpenAI to self-hosted Llama 3) with VRAM sizing, 4-bit quantization, vLLM inference server, and shadow-mode validation
• Built real-time Kafka streaming pipeline for patient vitals with partitioning by Patient ID and split-path processing to handle LLM latency