Kalpesh Rathod
Lecorpio (An Anaqua Inc Company), Director of Engineering
Fremont, California, United States
Actions
Kalpesh Rathod is Director of Software Engineering at Anaqua, the global leader in IP management software, where he leads engineering for an AI-driven platform that automates high-stakes financial decisioning at enterprise scale. He is a named inventor on a US patent covering AI-based confidence-scoring and workflow automation, and has authored peer-reviewed papers on agentic AI for financial automation and confidential AI systems for enterprise data. He recently delivered an invited keynote at the 10th International Joint Conference on Advances in Computational Intelligence (IJCACI 2026), published by Springer Nature, on building domain-specific AI for enterprise use. He holds a Bachelor of Engineering in Information Technology and completed Harvard Business School Leadership Principles program.
Area of Expertise
Topics
From Generic LLMs to Production-Grade Automation: Lessons from Building Enterprise AI at Scale
Most AI adoption talks focus on model capability. This one focuses on what happens after the model works: getting AI into a production system that a Fortune 500 company depends on for legally consequential, irreversible decisions. Drawing on a decade of building enterprise IP infrastructure including a patented confidence-scoring workflow engine and a production payment automation platform processing renewal decisions for intellectual property rights worldwide , this talk walks through the real engineering tradeoffs of deploying domain-specific AI where generic models fall short: policy-bound automation, human-in-the-loop escalation thresholds, and the audit and governance requirements that separate a demo from a system enterprises can actually trust. Attendees will leave with concrete patterns for deciding when to automate, when to keep a human in the loop, and how to build AI systems that hold up under real operational and regulatory scrutiny.
Confidential AI for Multi-Tenant Enterprise Platforms: Data Isolation Without Sacrificing Intelligen
Enterprise AI platforms serving multiple clients face a hard constraint most AI security talks skip past: how do you let AI retrieve and reason over sensitive client data without any risk of cross-tenant leakage, especially when that data includes unfiled or confidential information? This talk covers the design of a confidential retrieval-augmented generation (RAG) system built for multi-tenant IP SaaS platforms, using trusted execution environments (TEEs) and policy-bound data access to enforce hard isolation boundaries at the infrastructure level, not just the application layer. Drawing on published research and production engineering experience, I'll cover practical tradeoffs between security guarantees and retrieval quality, how to design policy enforcement that survives model updates, and lessons learned building AI infrastructure for clients who cannot tolerate data exposure under any circumstances.
Agentic AI for High-Stakes Deadlines: Automating Financial Decisions Without Losing Control
When missing a deadline permanently forfeits a client's legal rights, "move fast and iterate" isn't an option. This talk covers the design of an agentic AI system for automating maintenance-fee and spend decisions in enterprise IP operations, built to reduce cost and deadline risk while keeping humans authoritative over the decisions that matter. Drawing on published research and production experience, I'll cover how to scope agent autonomy safely, where policy-controlled guardrails belong in the decision pipeline, and how to design for auditability from day one rather than bolting it on after an incident. Practical patterns for anyone building agentic systems where mistakes are expensive and irreversible.
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top