cv
Basics
| Name | M. Moein Shariatnia |
| Label | MD & ML Researcher |
| moein.shariatnia@gmail.com | |
| Summary | MD and ML researcher specialising in medical imaging, multimodal learning, LLMs, and generative AI. 350+ citations (h-index 6) and 4+ years of large-scale R&D, with collaborations at Google DeepMind, Mayo Clinic, Stanford, Harvard, and Hospital for Special Surgery. Published at ICML, ICLR, MICCAI workshops and leading medical journals. Co-secured >$70k in competitive grants. |
Work
-
2024.01 - Present Machine Learning Researcher (Part-Time)
AP Healthtech LLC
Collaboration with Dr. Ayoosh Pareek's multidisciplinary team on AI for musculoskeletal imaging at Hospital for Special Surgery (HSS).
- Started as sole ML developer; early results led to >$70k in competitive grants (AOSSM, ON Foundation, ISHA) and growth to a team of 3 engineers
- Designed bone age prediction model from hand and knee X-rays (~3-month MAE, >20% over prior SOTA); built landmark detection pipeline with <1% keypoint error; model being integrated into clinical workflows
- Co-leading self-supervised foundation model for MSK imaging and MRI-to-CT translation via diffusion models; collaborated on trustworthy AI for medicine with Harvard researchers (Dr. Rajpurkar)
-
2023.05 - 2023.11 Machine Learning Developer (Part-Time, Contract)
Rocket AB
Built multimodal search pipeline for brand/logo conflict detection, Stockholm, Sweden.
- Built multimodal search pipeline (CLIP embeddings + classical NLP) for brand/logo conflict detection across 500k+ trademarks in NoSQL database; FastAPI backend <150ms latency; Dockerized and deployed on Azure
-
2021.06 - Present Independent Research Collaborator
Google DeepMind, Mayo Clinic, Stanford, RWTH Aachen
Multiple research collaborations across top institutions.
- DeepMind/UW: Large-scale distributed training (8x V100) on million-scale datasets; invented one-shot method with >10x compute savings. Papers at ICML 2022 and ICLR 2023
- RWTH Aachen/Stanford: Developed TransDeepLab, Swin-Transformer medical image segmentation (~200 citations, MICCAI)
- Mayo Clinic: Automated shoulder morphology measurement via keypoint detection (JSES 2022); lead developer of CONFLARE, conformal prediction for RAG (6k+ PyPI downloads); co-developed LatteReview multi-agent LLM framework
-
2021.03 - 2023.04 Machine Learning Developer (Part-Time)
Aris Co.
Led development of face-health computer vision application, Tehran, Iran.
- Led development of face-health CV application with personalised skincare recommendations; built end-to-end ML pipeline with 4 models (face detection, quality check, wrinkle/redness segmentation, skin classification) optimised for CPU inference; deployed via Django REST + Ray Serve (<20ms latency)
Volunteer
-
2025.01 - 2025.12 Workshop Lecturer
RSNA Annual Meeting, Chicago
Workshop on 'An Introduction to Multi Agent AI Systems in Radiology'.
-
2024.01 - 2024.12 -
2022.01 - Present Invited Reviewer
ICML/ICLR Workshops + PLoS ONE
Peer review for top ML conferences and medical journals.
Education
-
2018.09 - 2025.09
Awards
- 2025
- 2025
ON Education Grant
ON Foundation
$28,000 grant for osteoarthritis progression prediction using diffusion models
- 2024
AOSSM Playmaker Grant
AOSSM
$25,000 grant for AI-based bone age prediction from hand & knee radiographs
- 2025
- 2025
Selected Participant, M2L Summer School
Google DeepMind
Sponsored participation in M2L Summer School, Split, Croatia
- 2024
Travel Grant + Registration Waiver, EEML Summer School
Google DeepMind
EEML Summer School, Novi Sad, Serbia
- 2023
Shortlisted for Trainee Research Prize
Radiological Society of North America (RSNA)
Recognition for research excellence in radiology
- 2022
- 2022
- 2021
- 2020
- 2020
Solo Bronze Medal, Basic Sciences Olympiad
Iran's Ministry of Health
Bronze medal in national olympiad
- 2018
Fully Funded MD Scholarship
National University Entrance Exam
Ranked 39th out of >600,000 participants (top 0.01%)
Publications
-
2026 Deep learning Models, How to Develop and Deploy (Book Chapter)
Basic Methods Handbook for Clinical Orthopaedic Research
Book chapter on developing and deploying deep learning models. Forthcoming 2026.
-
2025 LatteReview: A Multi-Agent Framework for systematic review automation using large language models
arXiv (preprint)
Multi-agent LLM framework for automating systematic literature reviews.
-
2025 Towards trustworthy artificial intelligence in musculoskeletal medicine: A narrative review on uncertainty quantification
KSSTA
Narrative review on uncertainty quantification for trustworthy AI in MSK medicine.
-
2025 Determination of Skeletal Age From Hand Radiographs Using Deep Learning
American Journal of Sports Medicine (AJSM)
Deep learning for skeletal age determination with state-of-the-art accuracy.
-
2025 Artificial intelligence applications in musculoskeletal imaging
Current Reviews in Musculoskeletal Medicine
Review of AI applications in musculoskeletal imaging.
-
2024 CONFLARE: CONFormal LArge language model REtrieval
arXiv (preprint)
Conformal prediction framework for RAG pipelines.
-
2024 Predictive modeling for acute kidney injury after percutaneous coronary intervention
European Journal of Medical Research
ML model for predicting AKI following PCI in ACS patients.
-
2023 The role of pre-training data in transfer learning
MRL Workshop, ICLR 2023
How pre-training data distribution affects transfer learning in vision models.
-
2022 TransDeepLab: Convolution-Free Transformer-Based DeepLab v3+ for Medical Image Segmentation
PRIME Workshop, MICCAI 2022
Transformer-based medical image segmentation (~200 citations).
-
2022 Deep learning model for measurement of shoulder critical angle and acromion index
JSES Reviews, Reports, and Techniques
Automated shoulder morphology measurement from radiographs.
-
2022 How well do contrastively trained models transfer?
Workshop on Pre-training at ICML 2022
Transfer learning analysis of contrastive vision models with efficiency improvements.
Skills
| ML & Deep Learning | |
| PyTorch | |
| HuggingFace (Transformers, Diffusers) | |
| scikit-learn | |
| OpenCV | |
| Self-supervised Learning | |
| Transfer Learning | |
| Distributed Training (multi-GPU) | |
| Uncertainty Quantification |
| Computer Vision | |
| Classification | |
| Segmentation | |
| Keypoint Detection | |
| Medical Imaging (DICOM, NIfTI, MONAI) | |
| Diffusion Models | |
| GANs | |
| Vision Transformers | |
| CLIP |
| NLP & Generative AI | |
| LLM Fine-tuning | |
| Retrieval-Augmented Generation (RAG) | |
| Multi-Agent Systems | |
| Conformal Prediction | |
| Prompt Engineering |
| Engineering & Cloud | |
| Python | |
| FastAPI | |
| Django REST | |
| Ray Serve | |
| Docker | |
| Git | |
| Linux | |
| GCP | |
| AWS | |
| Azure |
| Research & Domain | |
| Grant Writing ($70k+ secured) | |
| Clinical Validation | |
| Study Design | |
| Scientific Writing | |
| Peer Review (ICML/ICLR) |
Languages
| Persian | |
| Native speaker |
| English | |
| Full professional proficiency |
Interests
| Machine Learning Research | |
| Computer Vision | |
| Multimodal AI | |
| Generative AI | |
| Medical Image Analysis |
| Open Source & Education | |
| Technical Writing | |
| Educational Content | |
| Open Source Contributions |
Projects
- 2021.01 - Present
Simple CLIP (PyTorch)
- 700+ GitHub stars
- Cited in papers at top ML venues
- 2023.01 - 2024.12
CONFLARE & Radiology QA with RAG
- 6,000+ PyPI downloads
- RSNA Trainee Prize shortlist
- 2025.01 - Present
LatteReview
- 250+ monthly PyPI downloads