Reza Baharani

I build production AI systems spanning real-time inference, distributed edge/cloud infrastructure, and agentic workflows. My work covers the full ML lifecycle—from data collection and architecture design to optimization, deployment, monitoring, and product delivery.

Currently, I’m a Senior AI Engineer at ForesightCares, where I architect production inference systems for clinical mobility assessment. Our platform performs real-time 3D human pose estimation at 30fps and supports multiple assessment protocols across at-home and clinical settings. This work led to a US Patent (12,343,138 B2) for AI-powered mobility assessment.

As a Research Scientist at TeCSAR Lab at UNC Charlotte, I developed self-supervised foundation models for human motion and distributed AI infrastructure for privacy-aware, real-time multi-camera inference. Our latest LLM-inspired human motion work has been accepted to BMVC 2026.

My research interests include:

AI Systems & Infrastructure — Distributed inference, hybrid edge/cloud deployment, observability, and MLOps
Efficient AI — Hardware/software co-design, model optimization, and power-efficient inference
Agentic AI — Multi-agent orchestration, generative AI workflows, and compliance automation
Self-Supervised Learning — Foundation models, discrete tokenization, and Vision Transformers
Human Motion Understanding — 3D pose estimation, action recognition, and clinical mobility analytics

I earned my Ph.D. in Electrical & Computer Engineering from UNC Charlotte, where I developed lightweight temporal convolutional networks for time-series classification on microcontrollers and contributed to algorithm/architecture co-design for FPGA-based DNN acceleration.

I have published 12+ peer-reviewed papers across IEEE and ACM venues, accumulating 657 citations (h-index: 11). My work has appeared in IEEE Transactions on Intelligent Transportation Systems, IEEE Internet of Things Journal, ACM Transactions on Embedded Computing Systems, and BMVC.

selected publications

BMVC

A Feasibility Study on Self-Supervised LLM-Inspired Training for Generalizable Human Motion Understanding

Mohammadreza Baharani, Ghazal Alinezhad Noghre, Armin Danesh Pazho, and 2 more authors

In British Machine Vision Conference, 2026

Accepted

Abs HTML

A feasibility study of self-supervised, LLM-inspired training for generalizable human motion understanding using discrete motion tokenization and Vision Transformer pretraining, achieving 89.4% action classification and 76.56% AUC-ROC on anomaly detection.
IEEE IoT

Ancilia: Scalable Intelligent Video Surveillance for the AIoT

Armin Danesh Pazho, Christopher Neff, Ghazal Alinezhad Noghre, and 4 more authors

IEEE Internet of Things Journal, 2023

Abs HTML

Ancilia presents a scalable intelligent video surveillance architecture for the AIoT, enabling distributed processing across edge and cloud infrastructure with privacy-preserving analytics.
ACM TECS

ATCN: Resource-Efficient Processing of Time Series on Edge

Mohammadreza Baharani and Hamed Tabkhi

ACM Transactions on Embedded Computing Systems, 2022

Abs HTML Code

ATCN presents attention-based temporal convolutional networks enabling fast time-series classification on resource-constrained embedded devices with formalized hyperparameters for application-specific architecture tuning. Deployed on Cortex-M7 consuming only 49% of 320KB RAM and 15% of 1MB flash.
IEEE TITS

DeepTrack: Lightweight Deep Learning for Vehicle Trajectory Prediction in Highways

Vinit Katariya, Mohammadreza Baharani, Nichole Morris, and 2 more authors

IEEE Transactions on Intelligent Transportation Systems, 2022

Abs HTML Code

This paper presents DeepTrack, a lightweight deep learning approach for vehicle trajectory prediction in highways using Temporal Convolutional Networks with depthwise separable convolutions, achieving state-of-the-art accuracy with significantly reduced computational complexity for IoT deployment.
IEEE IoT

Real-Time Deep Learning at the Edge for Scalable Reliability Modeling of Si-MOSFET Power Electronics Converters

Mohammadreza Baharani, Mehrdad Biglarbegian, Babak Parkhideh, and 1 more author

IEEE Internet of Things Journal, 2019

Abs HTML Code

A real-time LSTM-based reliability prediction system for power electronics converters, achieving scalable monitoring on IoT edge devices at 1.87W power budget.
IEEE IoT

REVAMP2T: Real-Time Edge Video Analytics for Multicamera Privacy-Aware Pedestrian Tracking

Christopher Neff, Matias Mendieta, Shrey Mohan, and 3 more authors

IEEE Internet of Things Journal, 2019

Abs HTML Code

An end-to-end scalable intelligent video surveillance system enabling privacy-aware multi-camera pedestrian tracking with real-time edge inference across distributed infrastructure on NVIDIA Jetson Xavier.