AI Systems Architect & Technology Leader

Chhavi
Jain

Writing about AI infrastructure, edge intelligence, and the engineering realities that hype cycles miss. 20+ years building the systems AI actually runs on.

20+
Years in Telecom & AI
40+
Patent Citations
150+
Engineers Led Globally
10x
Inference Gains at Qualcomm
Edge AI 5G / 6G TinyML LLMs & RAG Agentic AI IEEE SPS IIM Calcutta UIUC

Engineering at the
intersection of AI & wireless

Chhavi Jain is an AI systems architect and technology leader with 20+ years building large-scale telecommunications and machine learning platforms. She has led enterprise AI platform initiatives across financial services and technology, spent a decade at Qualcomm driving AI inference optimization and on-device ML powering billions of devices — partnering with Apple, Meta, Google, and Samsung — and founded Live AI Dream, a GenAI inference platform company built in partnership with Microsoft Azure and NVIDIA.

She holds an MS in Data Science & AI from UIUC, an MBA from IIM Calcutta, and is a recipient of the President of India Award, and a TinyML certification from Harvard. She serves as IEEE SPS Vice Chair and mentors at UCSD at the intersection of AI research and real-world impact.

Her technical work spans LLMs, RAG, agentic AI, quantization, and distributed systems. She has published IEEE research, holds multiple granted patents in 5G + AI systems, and has spoken at TinyML, IEEE Women in Engineering, and industry AI conferences globally.

2025 – Present
VP, Software Engineering
Fortune 500 Financial Services · $1.5T+ AUM · Enterprise AI Platforms
2022 – 2025
Founder & CEO — Live AI Dream
Microsoft Azure & NVIDIA Partner · Multi-LLM, RAG, Agentic AI · 35% client cost reduction
2012 – 2022 · 10 Years
Senior Staff Engineer / Manager — Qualcomm
On-device AI · 150+ engineers across USA, India, China · 10x inference gains · VP Excellence Award
2010 – 2011
Senior Engineer / Manager — Intel Mobile
3G Firmware Architecture · Star of the Quarter Award (CEO)
2007 – 2010
Senior R&D Engineer — Nokia
PHY / L1 Lead · 3G Infrastructure · Global Telecom Carriers
Education
MS AI & Data Science · UIUC
MBA IIM Calcutta · B.E. IT · President of India Award

Ideas on AI infrastructure,
edge intelligence & what hype misses

Published on Substack, Medium, and LinkedIn. Writing from 20 years inside the infrastructure AI depends on.

Technical talks & conference appearances

Speaking at the intersection of on-device AI, TinyML, wireless intelligence, and engineering leadership.

IEEE Women in Engineering · ILC 2021
Speaker Profile — IEEE WIE International Leadership Conference
View Profile →
Podcast · Startup Spotlight
Live AI Dream — Through the Corporate Glass Interview
Listen →

Where the real work happens

The engineering problems that don't make headlines — but determine whether AI works at scale.

01
Edge AI & TinyML
Moving AI workloads from centralized data centers to devices. Memory bandwidth, thermal, and connectivity constraints that determine whether edge AI actually functions. TinyML certified from Harvard.
02
AI Inference Optimization
Efficient model architectures, neural network acceleration, quantization (75% model size reduction), and the systems engineering behind 10x inference performance gains. Contributor to AIMET — Qualcomm's open-source AI Model Efficiency Toolkit (2.5k GitHub stars).
03
LLMs, RAG & Agentic AI
Multi-LLM orchestration, retrieval-augmented generation (85%+ accuracy), and agentic AI workflows built in production at Live AI Dream — delivered 35% average operational cost reduction for enterprise clients.
04
Wireless Network Intelligence
5G and next-generation infrastructure for AI-enabled devices. Radio resource management, power-efficient communication, and multi-radio coordination — the load-bearing network layer the GPU headlines miss.
05
Enterprise AI Platforms
Building AI systems that deliver measurable ROI at scale. From Fortune 500 enterprise platforms to startup product delivery — spanning financial services, automotive, and consumer electronics ecosystems.
06
Engineering Leadership
Built and scaled teams of 150+ engineers across 3 continents. VP Excellence Award (Qualcomm CTO). Star of the Quarter (Intel CEO). President of India Award. MBA IIM Calcutta.

Contributing to the
infrastructure layer

Notable open-source contributions from my decade at Qualcomm — tools used by researchers and engineers worldwide to optimize AI models for deployment on edge devices.

AIMET — AI Model Efficiency Toolkit

Advanced quantization and compression library for trained neural network models. AIMET enables INT8 and INT4 quantization with less than 1% accuracy loss — making large models deployable on edge devices like smartphones without retraining. Techniques include AdaRound, SeqMSE, Cross-Layer Equalization, and Quantization-Aware Training for PyTorch and ONNX models.

Quantization Model Compression Edge AI PyTorch ONNX INT8 / INT4 On-Device Inference
2.5k
GitHub Stars
430+
Forks
78+
Contributors
58+
Releases
View on GitHub →

International Innovation Portfolio

3 granted patent families in 5G + AI systems. 5 provisional families in Edge AI. Filed across the United States, Europe, China, and PCT.

40+

Patent citations from industry leaders across telecommunications and device manufacturing — reflecting the influence of these innovations on later generations of wireless and AI systems.

Cited by

Samsung Apple Ericsson Nokia Intel Qualcomm Xiaomi
Skipping Periodic Measurements to Enable Power Saving in User Equipments
US 11,129,103 B2 EP 3,766,289 A1 CN 111886903 B WO 2019/178574 A1
View Patent →
Quick Burst Tuneaway
US 11,134,364 B2 EP 3,888,416 B1 CN 113366918 B WO 2020/112473 A1
View Patent →
Cell Reselection Procedure for Frequencies Without Cell-Defining SSBs
US 10,716,044 B2 EP 3,884,712 B1 CN 113016213 A WO 2020/106826 A1
View Patent →

Full portfolio verification at patents.google.com

Let's talk about what's
actually happening in AI

Media inquiries, speaking engagements, collaboration, or a conversation about edge AI and the infrastructure layer.