About / Research Vision
I am a PhD candidate in the ECE department at UCLA, advised by Prof. Mani Srivastava. My research advances the intersection of machine learning, distributed systems, and cyber-physical systems (CPS), with applications in autonomous vehicles and the Internet of Things. My contributions include:
- Distributed inference architectures — developing optimization methods and systems for the latency-accuracy-energy Pareto frontier within real-time ML/FM pipelines across the device–edge–cloud continum, targeting platforms from NVIDIA H100-class clusters to resource-constrained Jetson devices [6,7].
- Foundation model systems — architecting FMaaS [2], FMTK [4], and TrustBench [1] as comprehensive frameworks for systematic benchmarking and deployment of large language models (LLaMA-3, Gemma-2), vision-language models (Qwen-VL, Moondream), and time-series foundation models (Chronos, Moment) across heterogeneous computating platforms [2].
- Cooperative Autonomy evaluation infrastructure — developing CADET [3], the first open-source testbed integrating CARLA simulator with high-fidelity network emulation and heterogeneous compute modeling to enable cooperative autonomy policy evaluation under realistic distributed system constraints.
- Production-scale implementations — from challenging traditional latency-accuracy trade-offs in distributed real-time inference pipelines [5] to deploying production-scale Amazon Sidewalk.
Prior to my doctoral studies, I contributed to IoT protocol design at Amazon Lab126 and studied automotive wireless systems at Bosch Research and Carnegie Mellon University. My research agenda focuses on establishing the theoretical foundations and systems infrastructure necessary for provably safe, resource-efficient, and high-performance distributed ML/FM architectures.
On-going Projects
CADET — Enabling Cooperative Autonomy via Distributed Experimentation Toolkit
A first-of-a-kind open-source toolkit for simulating distributed inference pipelines in autonomous vehicles. CADET integrates CARLA + ScenarioRunner with network delay emulation, energy profiling, and client-server pipelines for braking, perception, and control experiments.
FMaaS — Foundation Models as a Service
A research system exploring deployment strategies for foundation models on heterogeneous clusters. FMaaS uses ILP-based formulations to optimize cost, redundancy, and performance under varying workloads.
FMTK — Foundation Model Toolkit for Time-Series Data
A benchmarking and adapter suite for temporal foundation models. FMTK provides encoders, decoders, and adapters along with a standardized evaluation harness.
FM Zoo — Foundation Model Zoo for Heterogeneous Environments
A curated collection of open-source foundation models across vision, language, and time-series domains. FM Zoo standardizes interfaces and deployment scripts for diverse FMs, enabling plug-and-play experimentation on resource-constrained devices and distributed environments.
Industry Experience
Amazon Lab126
Embedded Software Engineer · 2019 - 2021
Designed Amazon Sidewalk IoT network from the ground up, enabling seamless connectivity for millions of Ring and Amazon devices across the 900 MHz spectrum with optimized low-power embedded systems firmware.
Impact & Achievements:
- Worked on the development of Amazon Sidewalk, a large-scale IoT network that now powers connectivity for Amazon, Ring, and third-party devices, reaching millions of households nationwide.
- Co-engineered a custom 900 MHz communication protocol optimized for ultra-low-power devices, balancing throughput, range, and battery efficiency to ensure seamless operation across diverse deployment scenarios.
- Drove improvement in flash memory efficiency by designing an end-to-end configuration management system with abstraction layers that intelligently moderated application-layer flash access.
- Built low-latency firmware bridging hardware and software layers, independently resolving critical production issues, and mentoring cross-functional teams to meet aggressive product launch timelines.
Bosch LLC, R&D Department
Wireless Systems Intern · 2018
Hardware-software co-design for ultra-precise vehicle localization achieving 30cm accuracy using Ultra-Wide Band technology, revolutionizing the keyless entry experience for next-generation vehicles.
Impact & Achievements:
- Collaborated with Bosch's Wireless Connectivity Group to implement the Perfectly Keyless project, a passive entry system designed to eliminate traditional car keys and provide a frictionless user experience.
- Engineered hardware and modeled advanced localization algorithms using Ultra-Wide Band (UWB) nodes strategically positioned on vehicles, achieving 30cm positioning accuracy.
Carnegie Mellon University
Graduate Research Assistant · 2018
Conducted cutting-edge research in automotive security, wireless systems, and network optimization across three major projects sponsored by Ford R&D, Argonne National Labs, and published in IEEE JSAC.
Ford R&D Sponsored
PEPS Car Security: Passive Keyless Entry Vulnerability Analysis
Served as Principal Investigator exposing critical vulnerabilities in passive keyless entry systems. Demonstrated man-in-the-middle attacks using Software-Defined Radios over 300ft range, delivering actionable security recommendations to Ford R&D that influenced next-generation vehicle authentication protocols.
IEEE JSAC 2019
Admission Control for Real-Time Interactive Video Sessions
Devised novel admission control algorithm to manage congestion and allocate resources for interactive video sessions. Designed and implemented WiFi (802.11g) testbed demonstrating 47% throughput improvement over traditional routers. Published in IEEE JSAC 2019 Special Issue on Multimedia Economics.
Argonne National Labs Sponsored
DSRC/WAVE Stack for V2V Communication Security
Developed open-source implementation of DSRC/WAVE stack on BladeRF (SDR) to emulate vehicle-to-vehicle communications. Engineered complete V2V information exchange infrastructure and analyzed security vulnerabilities in authentication mechanisms.
Selected Publications
FMTK: A Modular Toolkit for Composable Time Series Foundation Model Pipelines
Towards a Performance-Driven Device-Edge-Cloud Relationship
Procuring Spontaneous Session-Level Resource Guarantees for Real-Time Applications: An Auction Approach
Teaching
- [UCLA] Internet Customer Analytics by Prof. Sean Brüggemann.
- [UCLA] Forecasting and Time Series by Prof. William Yu.
- [UCLA] Logic Design of Digital Systems by Prof. Mani Srivastava.
- [UCLA] Mathematics for Life Sciences by Prof. Jane Shevstov.
- [CMU] Wireless Networks and Applications by Prof. Peter Steenkiste
Service
- Mentored 50+ undergraduate and graduate students for research projects and tech industry.
- Mentor, The Women of Color Project.
- Graduate Instructor, Los Angeles Computing Circle (CS Bootcamp 2022, 2023, 2024).
- Software Engineering Mentor, Amazon Mentorship Program.
- Head, Women in ECE (WinECE), Carnegie Mellon University, Silicon Valley.
- Campus Ambassador, Carnegie Mellon University, Silicon Valley.
- Program Representative, Student Council, ECE batch of 2017, VIT University.
Contact
Email: pragyasharma@ucla.edu · GitHub: @sharma-pragya