Tara Khani
Edge AI Innovations, CEO & Co-Founder
Actions
Tara is a results-driven leader and entrepreneur with a unique blend of engineering expertise and business acumen. Holding a Master's in Aerospace Engineering and an MBA, and with two published papers to her name, she founded Techsavvy Senior while pursuing her MBA, a company dedicated to bridging the technology gap between seniors and the younger generation. She then honed her skills as an application engineer and senior product manager at Keyence and Mitutoyo, global leaders in machine vision, automation, and sensor technology, where she led numerous successful POCs and projects. Transitioning to a customer success leadership role, Tara excelled at Ansys (a Synopsys company), managing multi-million-dollar projects for their virtual prototyping, digital twin, and simulation software solutions. She then joined SOTI, a global IoT and mobile device management software company, as an Enterprise Director, North American customers. Together with her co-founder and CTO, they founded Moorcheh.ai by Edge AI Innovations and developed their mvp, a revolutionary serverless vector search engine for RAG, transforming the landscape of AI multimodal assistants on edge device and/or cloud. They identified and addressed critical customer pain points, including lengthy reindexing, server maintenance complexities, accuracy limitations, scalability concerns, and security gaps.
Tara is passionate about bridging the gap between cutting-edge technology and impactful business solutions, drawing on her diverse experience to creatively solve customer challenges.
Links
Key Factors in Semantic Search Accuracy for RAG
This session will delve into the critical factors that directly influence semantic search accuracy within AI applications, particularly for Retrieval-Augmented Generation (RAG) systems. We will explore how the choice and configuration of a vector database fundamentally impact the quality of initial retrievals, and then demonstrate how reranker play a crucial role in further optimizing these results. Attendees will learn actionable strategies to fine-tune their semantic search pipelines, ensuring their AI and RAG implementations deliver highly relevant and factual information.
From Hallucinations to Factuality: Optimizing Vector DB for RAG, Best Practices, and Critical AI
This session will guide attendees through the essential considerations for selecting and implementing vector databases and rerankers to achieve highly accurate and reliable AI. We'll explore how vector database choice directly impacts the factuality of Retrieval-Augmented Generation (RAG) systems, present best practices for deployment and tuning across various use cases, and share real-world success stories from the finance, insurance, and healthcare sectors, demonstrating how precision in information retrieval is crucial for critical enterprise AI.
Your data, your control, your AI.
This session explores strategies to enhance Generative AI agents and Retrieval Augmented Generation (RAG) systems, focusing on accuracy, security, and scalability.
We will discuss:
Advanced Vector Search: Exploring the potential of vector search APIs and a novel alternative for implementing a high-performance vector database.
Deployment Strategies: Examining deployment options for Gen AI agents, including cloud (AWS, Azure, GCP) and edge AI platforms, with a focus on managing and optimizing these deployments.
Unlocking AI Infrastructure: We'll delve into strategies for owning your AI infrastructure, mitigating vendor lock-in, and achieving maximum flexibility and control in scaling your AI capabilities.
(Time permitting): We will explore exciting use cases for Generative AI on both cloud and edge devices, highlighting the benefits and challenges of bringing this transformative technology to smartphones and IoT devices.
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