Kunal Singh Pundir

About

Built and owned an end-to-end AI-driven decisioning platform at Uber, combining LLM orchestration with typed tool contracts and a Snowflake-based RAG pipeline to make decisions fully auditable. Delivered large-scale measurable impact (120k requests/day, 18k cases auto-resolved/month) while improving ops SLA from 3 days to 6 hours and cutting incident response time nearly in half. Previously led a high-risk strangler-fig modernization of a legacy insurance platform across 120+ microsites at Accenture, coordinating across multiple squads with feature-flagged parallel cutovers.

Experience

Education

Key Strengths

• Owned and shipped end-to-end production decisioning microservice (frontend, backend, data, infra) at Uber
• Productionized AI-native agentic decisioning with RAG grounding and auditable reasoning traces/source citations
• Designed robust testing strategy (unit + integration) focused on schema/tool contracts and escalation edge cases
• Defined and operationalized SLOs with cross-functional partners (PM/DS/SRE) and built monitoring/alerting
• Improved operational outcomes: 120k API requests/day; 18k cases auto-resolved/month; ops SLA reduced from 3 days to 6 hours
• Reduced median incident response time from 15 minutes to under 8 via alerting and operational instrumentation
• Led high-risk legacy modernization using strangler fig + feature flags + parallel run/rollback to avoid regressions
• Embedded across 5 delivery squads with minimal oversight; unblocked work by triaging by blast radius and maintaining a decisions log
• Strong stakeholder tradeoff management (speed vs auditability) translating ambiguous goals into phased roadmap