Yogendra Nalam

About

GenAI/ML engineer with production experience at Cognizant and Ally Financial, building end-to-end LLM/RAG systems and ML pipelines. Delivered a domain chatbot trained from 90k tickets and 45k docs, improving intent accuracy (65%→83%), scaling to 800+ concurrent users with 99.2% uptime and sub-150ms latency, and driving +14% customer satisfaction. Strong in Azure ML + DevOps CI/CD, Dockerized deployments, and explainable/PII-safe modeling using SHAP/LIME to satisfy stakeholder trust and GDPR needs.

Key Strengths

• Built and led production GenAI chatbot from 90k support tickets + 45k documents into a structured knowledge base
• Improved intent recognition accuracy from 65% to 83% via multi-stage spaCy preprocessing (lemmatization/NER, parsing, deduplication)
• Implemented RAG with Elasticsearch enabling real-time knowledge updates without retraining
• Scaled system to 800+ concurrent users with 99.2% uptime and <150ms response times (hybrid RAG search)
• Created Tableau monitoring for fallback rates and resolution to rapidly close knowledge gaps
• Azure ML Pipelines + Azure DevOps CI/CD automation; reduced model maintenance time by 40%
• Ensured environment consistency across teams by containerizing models with Docker
• Data-driven evaluation approach using golden datasets and automated tests for F1/latency/hallucinations pre-production
• Used SHAP/LIME to make models explainable to stakeholders and support GDPR-aligned decisioning
• Cross-functional collaboration with retention managers and legal to deploy compliant AI solutions; reduced attrition by 15% and increased customer satisfaction by 14%

Experience

Education

Skills

Languages