Nagendra Reddy Palugulla

About

Built and shipped a production real-time content moderation platform for Zoom/WebEx-style meetings, combining Whisper speech-to-text with fast NLP classifiers and REST APIs to flag hate speech, bias, and HIPAA-related content under strict latency constraints. Demonstrates strong MLOps/infra depth (Airflow, Kubernetes, Terraform/Helm, observability) and a pragmatic approach to reducing false positives via threshold tuning, context validation, and hard-negative data—while partnering closely with compliance and product stakeholders.

Experience

Education

Key Strengths

• Built and deployed a real-time AI content moderation system for live meetings (audio + chat) with near-real-time alerts
• Strong low-latency production engineering (rolling chunk processing, lightweight models, warm in-memory REST services, latency monitoring)
• Systematic false-positive reduction (threshold tuning, context checks across chunks, hard-negative dataset expansion)
• Production-grade orchestration experience (Airflow DAGs with SLAs/monitoring; idempotent pipelines; readiness checks; backfill/retry safety)
• Kubernetes deployment maturity (IaC with Terraform/Helm, config consistency across environments, resource management with probes/limits)
• Reliability-focused AI/agent workflow design (measurable success criteria, guardrails, schema validation, traceable end-to-end logging)
• Strong observability and online quality monitoring practices (tracing, dashboards, drift/quality proxy tracking, safe failovers)
• Effective translation of compliance/product needs into measurable ML requirements (e.g., acceptable false positive rates, alert severity, human review triggers)