Sairaghav Nissankula

About

ML/GenAI engineer with strong end-to-end production ownership across predictive ML, RAG systems, and LLM routing. They pair solid platform engineering skills with measurable business impact, including 15% churn reduction, 35% support ticket deflection, 45% GenAI cost savings, and a shared inference library that cut deployment time from weeks to days.

Key Strengths

• Owned end-to-end churn prediction system from experimentation to deployment and monitoring
• Drove 15% churn reduction and improved retention revenue
• Strong production ML monitoring and retraining strategy using PSI, KPI thresholds, and staged rollouts
• Shipped RAG-based support assistant with rigorous quality and safety evaluation
• Improved support ticket deflection by 35% and cut answer-finding time by more than half
• Deep hallucination mitigation expertise with grounding, retrieval thresholds, and post-generation verification
• Translated LLM routing research into production with cost, latency, and safety tradeoff management
• Reduced GenAI serving cost by 45% while maintaining quality on high-stakes requests
• Improved routed model quality by 18% through production feedback-driven iteration
• Built shared ML inference library that standardized serving across teams
• Accelerated model deployment from 1-2 weeks to 1-2 days
• Reduced serving-related bugs by roughly 70%

Experience

Education

Skills

Languages