Harshavardhan Garikala

About

Red Hat ML/LLM engineer who designed and deployed a production LLM-powered customer support automation system using RAG, improving latency by 30% via PEFT and vector search optimization. Built security and governance into retrieval (access-level filtering, encrypted Pinecone/ChromaDB) and delivered SHAP-based explainability via a dashboard for non-technical stakeholders. Experienced orchestrating distributed ML/RAG pipelines across AWS SageMaker and OpenShift with Airflow/Prefect, plus multi-agent workflows using CrewAI and LangGraph.

Experience

Education

Key Strengths

• Reduced vector search response time by 30% without degrading contextual relevance
• Production deployment of LLM/RAG system automating customer service responses
• Strong security-by-design for RAG (access-level filtering + encrypted vector stores)
• Explainability implementation using SHAP with stakeholder-facing dashboard
• Orchestrated 15+ ML workflows using Airflow + MLflow
• Scalable distributed pipeline design across AWS SageMaker and OpenShift using containerized tasks
• Reliability engineering in orchestration (retries, SLAs, health checks, monitoring)
• Multi-agent workflow design with clear roles and measurable success metrics
• End-to-end evaluation approach (unit/integration tests, offline benchmarks, online A/B tests)