Harshith.
Résumé · current as of June 2026

Harshith Chennupati

AI/ML engineer for biomedical signals, medical imaging, and deployable clinical systems.

Download PDF
harshith@chennupatis.com · +1 443 615 9830
Summary

I build end-to-end ML systems that turn clinical and physiological data into validated, shippable outputs — sleep staging and fragmentation from multi-modal biosignals, ECG respiratory-rate estimation, GPU-accelerated 3D imaging pipelines, and tooling that puts models in the hands of clinicians.

Education
2024 → May 2026 (expected)
M.S.E., Electrical & Computer Engineering
Johns Hopkins University · Baltimore, MD

GPA 3.8/4.0 · AI, Biomedical Signal Processing, Medical Imaging, Medical Device Design · Deep Learning, ML for Signal Processing, ML for Medical Applications, Computer Integrated Surgery

2020 → Jun 2024
B.Tech, Electronics & Communication
SRM Institute of Science & Technology · Chennai, India

GPA 3.76/4.0 · Embedded Systems, Signal Processing, FPGA Design

Experience
Jan 2026 → Present
Algorithms Engineer
Neurava · Baltimore, MD

Wearable sleep staging via PSG-to-IMU distillation, IMU pose estimation, and team MLOps.

  • Built a PSG-teacher to IMU-student knowledge distillation pipeline for wearable sleep staging on the DREAMT corpus; benchmarked classical biosignal baselines (Cole-Kripke, vanHees) against transformer-based sequence models with a rigorous evaluation harness across paired biological corpora.
  • Developed IMU-based human pose estimation with clustering (K-means, GMM, HDBSCAN) on bicep-mounted sensor streams; authored the ground-truth labeling protocol for posture-class validation.
  • Established MLOps practices for the team: experiment tracking, dataset versioning, reproducible training configs, and evaluation dashboards for fast iteration.
May 2025 → Present
Research Assistant
ISTAR Lab · Johns Hopkins · Baltimore, MD

Cross-modality 3D synthesis, GPU vision pipelines, multimodal acquisition, and clinician-facing inference tooling.

  • Built MAISI-US, a ControlNet-conditioned 3D latent diffusion pipeline adapting NVIDIA's MAISI foundation model to cross-modality ultrasound-to-CT synthesis. First reported adaptation of MAISI to a non-CT input modality; trained only the ControlNet branch on 9,068 paired US-CT volumes for low-cost domain transfer while keeping the VAE and diffusion backbone frozen.
  • Designed a multi-metric evaluation protocol (PSNR, mutual information, gradient orientation agreement, LPIPS) against paired ground truth, with parameter sweeps on inference steps, ControlNet scale, and noise factor for reproducible characterization of model behavior.
  • Built GPU-accelerated 3D vision pipelines (volumetric resampling, 3D-2D registration, DRR generation) on a CUDA-based imaging library; implemented pose regression with a custom Res-UNet for real-time 2D-in-3D visualization.
  • Led multimodal data acquisition integrating Clarius and Alpinion ultrasound probes, Medtronic O-arm CBCT, NDI optical tracking, and scripted Universal Robot (UR3) sweeps to produce a paired calibrated 3D dataset for training and quantitative evaluation.
  • Shipped Qt-based tooling for 3D Slicer to orchestrate deep-learning inference, putting research models directly into the hands of clinicians and researchers.
Spring 2025 → —
Biomedical Signal Processing Intern
Vigo · Remote

ECG-based respiratory estimation and accelerometer posture classifiers for a wearable monitoring product.

  • Designed ECG-based respiratory rate estimation using CEEMDAN, discrete wavelet transforms, and peak detection, achieving 2.5 bpm MAE on the BIDMC dataset.
  • Implemented and unit-tested accelerometer-based posture classifiers for a wearable monitoring product.
Fall 2025 → —
Teaching Assistant
Deep Learning for Medical Imaging · Johns Hopkins · Baltimore, MD

Course support for CNNs, segmentation, and multimodal registration.

  • Designed and graded assignments on CNNs, segmentation networks, and multimodal registration.
  • Mentored students on PyTorch implementations, training diagnostics, and evaluation.
Jul 2022 → Aug 2022
Engineering Intern
Life Signals · Bangalore, India

ECG biosensor testing and optimization in hospital environments for FDA-approved wireless devices.

  • Optimized ECG data collection and testing procedures in hospital environments for FDA-approved wireless biosensors.
  • Contributed to A2 ECG biosensor design; gained hands-on exposure to medical-device SoC and embedded workflows.
Selected projects
Jan 2026 — present
Sleep Staging
Neurava

Sleep-staging and biosignal ML for a clinical wearable — building evaluation pipelines that compare deep sequence models and classical baselines against polysomnography ground truth. Proprietary work; details limited by NDA.

2025 — present
MAISI-US
ISTAR Lab · Johns Hopkins

ControlNet-conditioned 3D latent diffusion adapting NVIDIA's MAISI foundation model for ultrasound to CT synthesis using paired cadaver US-CT ROIs, VAE latent pre-encoding, and a multi-metric validation suite (PSNR, SSIM, LPIPS, GOA).

Jun 2026
MedDataMCP
Open Source

Unified MCP server for federated medical/biosignal dataset discovery — one query across PhysioNet, NSRR, Zenodo, HuggingFace, OpenNeuro, and Kaggle, returning ranked, normalized results for LLM clients.

Fall 2024
3D Point-Cloud Registration & Surgical Navigation
Computer Integrated Surgery · Johns Hopkins

Implemented 3D registration, calibration, error-modeling, and distortion-correction modules; cut ICP runtime 40% with bounding-volume hierarchies and reduced EM-tracking positional error by 30%.

Spring 2025
Pneumothorax Detection & Segmentation
ML for Medical Applications · Johns Hopkins

Trained a multi-task U-Net with residual blocks on the SIIM-ACR pneumothorax dataset; achieved IoU 0.65 and 80% accuracy with a custom class-imbalance loss.

Spring 2025
Deep Unrolled Networks for MRI Reconstruction
Compressed Sensing · Johns Hopkins

Implemented ISTA-Net and ADMM-Net for accelerated MRI reconstruction from 25% undersampled k-space; extended ADMM-Net with Squeeze-and-Excitation blocks for 1.14× speedup at 24 dB PSNR.

Fall 2024
COPD Diagnosis from Lung Sounds
Design of Advanced Systems · Johns Hopkins

Engineered an at-home diagnostic ML pipeline from smartphone-recorded lung sounds using feature extraction, filtering, and classification on the ICBHI dataset — 95% accuracy on clean data.

Fall 2024
Noise-Resilient Emotion Recognition
ML for Signal Processing · Johns Hopkins

Improved noisy-audio classification accuracy from 18% to 51% using MetricGAN+ denoising and Wav2Vec2 features; gained an additional 20% via HuBERT and BERT multimodal fusion on the MELD dataset.

2025
3D Slicer Inference Tooling
ISTAR Lab · Johns Hopkins

Shipped Qt-based extensions for 3D Slicer that orchestrate deep-learning inference, so researchers and clinicians can run models without leaving the imaging environment.

Spring 2025
Respiratory Rate from ECG
Vigo

A signal-processing pipeline that estimates respiratory rate directly from a single-lead ECG, achieving 2.5 bpm MAE on the BIDMC benchmark.

Skills
ML & Deep Learning
PyTorch · TensorFlow · MONAI · Hugging Face · Diffusers · Transformers · CNNs / U-Net · Latent Diffusion · Knowledge Distillation · Self-Supervised Pretraining
Biomedical Signals & DSP
ECG · EEG · EMG · IMU · PSG · CEEMDAN · DWT · Spectral Analysis · Peak Detection · Cole-Kripke · vanHees · Actigraphy
Medical Imaging & 3D CV
3D Registration · ICP · DRR / FDK · Volumetric CNNs · Point Clouds · ITK · VTK · 3D Slicer · Open3D · OpenCV
Systems & Performance
CUDA · TensorRT · ONNX · Multi-GPU Training · Real-Time Inference · Linux · Profiling
MLOps & Cloud
Weights & Biases · Docker · Git / CI · AWS (EC2 · Lambda · S3) · Dataset Versioning · pytest · Evaluation Harnesses
Languages
Python · C / C++ · CUDA · MATLAB · SQL · JavaScript · Bash