Ali Quidwai

I’ve always been drawn to building things that matter. After finishing my Computer Science degree in India, I joined Carcrew as Technical Lead—a scrappy automotive startup where I learned what it takes to ship products that real people use. I built the product and team from scratch—learning what it takes to ship fast and iterate faster. It was exhilarating, but something kept nagging at me: I wanted to go deeper.

That pull brought me to NYU Tandon for my MS in Computer Engineering, where everything changed. Working with Prof. Dennis Shasha, Prof. Manpreet Katari, and Prof. Parijat Dube (IBM Research) opened my eyes to the beauty of deep learning—not just as a tool, but as a way of thinking about problems. As an Entrepreneurial Fellow, I conceptualized and built AYA, an EdTech startup that got selected for NYU’s Entrepreneurial Sprint (10 of 150). I published my first paper at ACL 2023 (BEA Workshop) on detecting AI-generated text. Graduated with Honors. But more importantly, I found my calling: using AI to solve problems where the stakes are real.

Now I’m at Mount Sinai, building AI systems for precision oncology. The work is hard—when a clinician uses your tool to make treatment decisions, there’s no margin for error. I’ve built multi-agent systems that extract genomic evidence (OncoCITE: 97.8% precision, submitted to Nature Cancer), GPU pipelines that turned week-long workflows into 3-hour runs (92.3% time reduction), and fine-tuned voice ASR for clinical terminology. Research includes a widely cited clinical RAG framework (35+ citations) and first-author work at ACL (BEA Workshop).

Outside of work, I’m focused on two things: open source and interpretability. I’ve built a lot of tools that stayed locked in production—this year I’m changing that. This site is where I’ll document what I’ve learned and release projects for others to use and improve. I’m also deep in the weeds of model interpretability, participating in SPAR and other AI safety programs. After years of making models work, I want to understand why they work—and when they don’t.

If you’re curious about multi-agent systems, clinical AI, or interpretability—I’d love to connect. The best ideas come from unexpected conversations.

news

Jan 15, 2025	Presenting OncoDIF and PRIME Model at ASH 2025 - our multi-agent framework for genomic curation and predictive relapse indicators for myeloma patients receiving T-cell engagers.
Jan 10, 2025	OncoDIF published in Blood 2025 - An auditable AI framework for automated genomic curation achieving 97.8% precision in novel discovery with 0% critical errors.
Mar 14, 2024	RAG Chatbot for Multiple Myeloma preprint on medRxiv - Now at 36 citations. Production RAG system for precision medicine achieving 88% effectiveness.

latest posts

Jan 16, 2026	Why I'm Finally Building in Public
Jan 16, 2026	MedGemma 1.5: Google's Open Medical AI Just Got Serious

selected publications

Nature Cancer
OncoCITE: AI-Driven Genomic Evidence Curation for Hematologic Malignancies

Mujahid Ali Quidwai, Santiago Thibaud, Sundar Jagannath, and 2 more authors

Nature Cancer, 2025

Submitted to Nature Cancer

Abs Bib

We present OncoCITE, a multi-agent AI system for automated genomic evidence extraction from scientific literature. Through systematic exploratory data analysis on the CIViC database (11,312 evidence items, 3,083 publications), we quantified 12 structural bottlenecks including curation latency (median 31 days, P90 >21 months) and emerging target gaps. Our 6-agent architecture using Claude Agent SDK with 22 MCP tools achieves 84% ground truth recovery, 97.8% novel discovery precision, and 0% critical errors on a 15-paper validation corpus. A novel three-way validation framework identified 24.2% curation errors in expert-curated databases.
@article{quidwai2025oncocite, title = {OncoCITE: AI-Driven Genomic Evidence Curation for Hematologic Malignancies}, author = {Quidwai, Mujahid Ali and Thibaud, Santiago and Jagannath, Sundar and Parekh, Samir and Lagana, Alessandro}, journal = {Nature Cancer}, year = {2025}, note = {Submitted to Nature Cancer}, }
medRxiv
A RAG Chatbot for Precision Medicine of Multiple Myeloma

Mujahid Ali Quidwai and Alessandro Lagana

medRxiv, 2024

36 citations

Abs DOI Bib HTML

We developed a production Retrieval-Augmented Generation (RAG) system for clinical decision support in multiple myeloma. The system uses LangGraph orchestration, BAAI/bge-large-en-v1.5 embeddings for semantic retrieval, and Mistral-7B for generation. Processing 5,000+ clinical documents, we achieved 88% clinical effectiveness. The first prototype was deployed and actively used by 2-3 clinicians at Mount Sinai for multiple myeloma research and treatment planning, demonstrating the feasibility of production RAG systems in healthcare settings.
@article{quidwai2024rag, title = {A RAG Chatbot for Precision Medicine of Multiple Myeloma}, author = {Quidwai, Mujahid Ali and Lagana, Alessandro}, journal = {medRxiv}, pages = {2024.03.14.24304293}, year = {2024}, doi = {10.1101/2024.03.14.24304293}, note = {36 citations}, }
ACL
Beyond Black Box AI-Generated Plagiarism Detection: From Sentence to Document Level

Mujahid Ali Quidwai, Chunhui Li, and Parijat Dube

In Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023), 2023

31 citations, IBM Research

Abs DOI Bib HTML Website

We present a novel multi-faceted NLP approach for detecting AI-generated text in educational settings. Our method employs contrastive loss training and LLM-generated paraphrases to achieve 94% accuracy in human-AI text classification. Unlike black-box approaches, our system provides interpretable signals at both sentence and document levels, enabling educators to understand the nature and extent of AI involvement in student submissions. This work was conducted in collaboration with IBM Research.
@inproceedings{quidwai2023plagiarism, title = {Beyond Black Box AI-Generated Plagiarism Detection: From Sentence to Document Level}, author = {Quidwai, Mujahid Ali and Li, Chunhui and Dube, Parijat}, booktitle = {Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023)}, year = {2023}, organization = {Association for Computational Linguistics}, doi = {10.18653/v1/2023.bea-1.58}, note = {31 citations, IBM Research}, }
ASH
Development of Predictive Relapse Indicators for Myeloma T Cell Engagers (PRIME) Model for Myeloma Patients Receiving BCMA- and GPRC5D-Targeting T Cell Engagers

Tarek H. Mouhieddine, Tony Sheng, Junia Vieira Dos Santos, and 8 more authors

Blood, 2025

ASH 2025 Conference Abstract, Contributing Author

Abs DOI Bib HTML

We developed the PRIME (Predictive Relapse Indicators for Myeloma T-Cell Engagers) model for patients receiving BCMA- and GPRC5D-targeting T-cell engager therapies including teclistamab, elranatamab, and talquetamab. By integrating clinical, genomic, and treatment response data, we identified early relapse indicators enabling risk stratification at treatment initiation and monitoring strategy optimization. The model supports clinical decision-making for the growing landscape of bispecific antibody therapies in multiple myeloma.
@article{mouhieddine2025prime, title = {Development of Predictive Relapse Indicators for Myeloma T Cell Engagers (PRIME) Model for Myeloma Patients Receiving BCMA- and GPRC5D-Targeting T Cell Engagers}, author = {Mouhieddine, Tarek H. and Sheng, Tony and Vieira Dos Santos, Junia and Aleman, Adriana and Avigan, Zachary and Siegel, Ariel and Quidwai, Mujahid Ali and Chari, Ajai and Jagannath, Sundar and Parekh, Samir and Lagana, Alessandro}, journal = {Blood}, volume = {146}, number = {Supplement 1}, pages = {3996}, year = {2025}, doi = {10.1182/blood-2025-3996}, note = {ASH 2025 Conference Abstract, Contributing Author}, }