Hi, I'm Vibhor Gupta
About Me
I'm Vibhor Gupta — a Senior mmWave Modem Software Engineer at Qualcomm who architects the RF algorithms powering next-generation wireless systems.
I've led the commercialization of industry-first technologies, including Qualcomm's pioneering DSDA+V2X modem and frequency-independent sideband suppression algorithms that deliver measurable SNR improvements. My work spans from low-level embedded systems optimization to cutting-edge CNN models for RF performance prediction — bridging traditional signal processing with modern AI.
Armed with a 4.11/4.0 GPA Masters from University of Michigan EECS and a top-tier Bachelor's from NIT Hamirpur, I bring both academic rigor and proven industry impact. My expertise includes 5G/6G protocols, real-time embedded systems, reinforcement learning, and mmWave RF design — a rare combination that positions me at the forefront of wireless innovation.
What sets me apart? I don't just implement algorithms — I reimagine them to solve critical real-world challenges. Whether it's enabling healthcare access in under-served regions, optimizing spectrum utilization for next-generation networks, or aligning AI systems, every project I pursue is driven by the passion to bridge technology gaps that impact lives and industries at scale.
I'm passionate about solving the complex challenges that define the next decade of connectivity. Ready to discuss how I can drive breakthrough innovations at your organization? Let's connect.
Work Experience
Qualcomm, CA, USA
mmW Modem SW Engineer
Leading the effort to bridge the gap between the fields of Wireless Communication and Machine Learning Algorithms.
- Redesigned FR1/FR2 Rx algorithms, including AGC and SPURLIC, to enhance RF performance.
- Developed a CNN model for frequency-independent IQ imbalance prediction, validated feasibility for hardware integration.
University Of Michigan, MI, USA
Research Assistant, Guided by Prof. Lei Ying
Working on development of a Reinforcement Learning algorithm to handle scheduling and queue length management under heavy traffic conditions in Wired and Wireless Communication Systems.
- Implemented a Multi-step Deep Q Network Target, to solve a complex queue serving problem, in a Criss-Cross Network.
Qualcomm, CA, USA
mmW Modem SW Intern
Redesigned and implemented an algorithm in a Real Time Embedded System, that allows for a faster convergence of Residual Side Bands in a direct conversion receiver.
- Re-designed an algorithm for Frequency Independent Side Band suppression which provides SNR improvements.
- Revamped the call-flows between co-procs to allow for faster convergence times, and less memory operations.
- Delivered significant optimizations to Sideband Calibration timeline by 30%.
Qualcomm, Hyderabad, IN
V2X RFSW Engineer
Spearheading the design and commercialization of the first DSDA+V2X modem.
- Led LTE -V2X RFSW team for design, commercialization and support for the first DSDA+V2X Modem by Qualcomm.
- Developed RFSW solutions maintaining functionality of LTE, NR V2X as per the 3GPP spec (ex: ACLR, SEM, EVM).
- Focused on Physical layer programming of front end embedded HW modules (PLLs, LNAs, PAs) to facilitate communication and transfer of data across protocol layers.
- Execution of a Real time Embedded System environment with close time and memory constraints to honor the SW architecture and enable a reliable modem subsystem.
Samsung Research, Noida, IN
Network Engineer
Developed Modem protocol procedures for support in Galaxy A Devices.
- Troubleshot Modem protocol procedures for support in Galaxy A Devices, delivering 3GPP compliant performance.
- Analyzing the protocol logs across RRC, MAC, debugged Handover and CSFB Scenarios to establish the root cause.
- Designing and developing interface between modem and application, call processing of 3GPP/GSM/LTE/IMS.
Research Projects
RL for NLP Tasks
University Of Michigan, MI, USA
This project investigates methodologies for enhancing the performance of small language models by aligning them with user intent across diverse tasks with Reinforcement Learning from Human Feedback (RLHF).
REDD - Real-Time Disease Detection
University Of Michigan, MI, USA
A Real-time Expedited Disease Detection application for Low Resource Countries. Our system allows doctors to upload chest x-ray scans and receive segmented output with diagnosis up to 80% confidence score.
TCP in mmW Networks
University Of Michigan, MI, USA
Implemented a new TCP algorithm for mm-wave networks, carried extensive analysis, and suggested improvements for current TCP algorithms catering to mm-wave network requirements.
Cognitive Radios in 5G
TU Wien, Vienna, Austria
Increasing Spectrum Efficiency by Channel Detection, an implementation for Cognitive Radio in 5G Networks to optimize spectrum utilization.
Let's Connect
I'm always open to discussing new opportunities, collaborations, and innovative projects in the field of wireless communications and embedded systems.