Smridhi Gupta
h Analyst @ Citibank | Building Trustworthy AI Systems | 7K+ Tech Community
Pune, India
Actions
Smridhi Gupta is a Tech Analyst at Citibank specializing in secure LLM systems, RAG reliability, and AI evaluation frameworks. Previously a Research Intern at AIISC, she has authored six peer-reviewed publications spanning transformer-based medical imaging, enterprise AI, and applied machine learning research. Her work focuses on building trustworthy, production-ready AI systems that bridge research and real-world deployment. She is also a tech creator sharing insights on AI, development, and emerging technologies with a growing community of 6.5K+ followers.
Beyond research and engineering, she is the organizer of JS Community, where she has led 4+ offline tech events in the past four months in Pune, building a growing developer ecosystem with 350+ signups and an average footfall of 100+ attendees per meetup.
Area of Expertise
Topics
AI That Survives Production
LLM-powered applications are moving from demos to production, and that’s where most teams discover their blind spots. From prompt injection and tool misuse to privacy leaks and silent model drift, deploying AI systems introduces risks that traditional cloud architectures were never designed to handle.
In this session, we’ll walk through a practical five-pillar framework for hardening AI systems in real-world environments. Attendees will learn how to design defensive prompts, validate inputs and outputs, enforce safe tool permissions, protect sensitive data, and monitor probabilistic systems after deployment.
This talk focuses on building AI systems that don’t just work in staging, but survive in production.
Inference Engineering with gRPC: Building Low-Latency AI Systems That Scale
Inference engineering is the biggest bottleneck in LLM-based AI systems today. Modern AI platform are increasingly relying on gRPC instead of REST, for communication between inference gateways, model servers, retrieval services, and orchestration layers because every millisecond matters.
This session introduces the engineering principles behind low-latency AI inference. It also highlights the tradeoffs between gRPC and REST as the protocol of choice for production LLM systems. Attendees will compare REST and gRPC for inference workloads, understand unary and streaming RPCs for real-time token generation, and learn how deadlines, cancellation, flow control, retries, and backpressure improve reliability under load. The session also explores how modern LLM serving stacks use gRPC to build scalable inference pipelines. Attendees will leave with practical guidance for designing faster, more resilient AI services using patterns they can immediately apply.
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