Teja Babu Mandaloju

About

AI/ML engineer who led production deployment of a multimodal (text/video/image) RAG system on GCP using Gemini 2.5 + Vertex AI Vector Search, scaling to 10M+ documents with sub-second latency and +40% retrieval accuracy. Strong MLOps/orchestration background (Kubernetes, CI/CD, Airflow, MLflow) with proven impact on reliability (75% fewer incidents) and deployment speed (92% faster), plus experience delivering explainable ML (XGBoost + SHAP + Tableau) to non-technical retail stakeholders.

Experience

Education

Key Strengths

• Led production deployment of a multimodal RAG system (text/video/image) for enterprise knowledge retrieval
• Scaled vector search to 10M+ documents with sub-second latency using FAISS + caching
• Improved retrieval accuracy by 40% through system and evaluation improvements
• Reduced production incidents by 75% via drift detection and monitoring
• Cut deployment time by 92% by implementing automated CI/CD pipelines
• Improved LLM response quality by 35% using LangChain-based prompt engineering
• Deep Airflow orchestration experience: modular DAG design, dependency management, sensors/branching, and scheduler performance optimization
• Designed rigorous AI agent/workflow testing: unit/integration tests, ground-truth eval sets, adversarial/prompt-injection testing, offline + online metrics
• Drove measurable online improvements via A/B testing and feedback loops (e.g., 28% reduction in negative feedback after video retrieval fixes)
• Strong cross-functional delivery: translated retail churn needs into an explainable XGBoost solution (94% AUC-ROC) with SHAP + Tableau for business stakeholders