Hi, I’m Massad.
I build pipelines that turn research into production.
At the Rutgers Turfgrass Pathology Lab I’m architecting a distributed, 19-node LangGraph pipeline — a full-stack system (React/TypeScript, FastAPI, PostgreSQL + pgvector) that integrates 9 external data sources and is designed to scale to 100+ concurrent users in production. The same lab is also where I built a hybrid disease-forecasting model, a viable alternative to the classic Smith-Kerns baseline on real held-out data.
The path here
Nov 2025 to now
ML Research Assistant, Rutgers Turfgrass Pathology Lab
Started the two-stage hybrid dollar spot model, evaluated against the Smith-Kerns baseline.
StudyBuddy
RAG pipeline with LangChain + FAISS, 500-token chunking, adaptive practice questions.
AI/ML Fellow, Break Through Tech — Cornell Tech
Selected from 4,000+ applicants. Income-eligibility classifier on Census data.
Software Engineer Intern, Rutgers Turfgrass Pathology Lab
Architecting the 19-node LangGraph pipeline behind the lab's weekly newsletter.
Data Analytics & AI Skills Playbook
14 portable AI-assisted ML workflows; caught a 13-point precision drop from overfitting.
Manuscript in preparation
Writing up the dollar spot results with my professor and a plant-pathology domain expert.
How the pipeline is built
A 19-node LangGraph system, end to end
Orchestrate the pipeline with LangGraph
A 19-node, DAG-based pipeline integrates 9 external data sources through the Anthropic and OpenAI APIs, designed to scale to 100+ concurrent users in production — not a single script, a real orchestrated system.
Build the subscriber-facing surface
A React/TypeScript frontend talks to a FastAPI backend for the newsletter signup flow — form validation, duplicate detection, automated confirmation emails via SendGrid, and one-click unsubscribe, all backed by PostgreSQL.
Design the data layer
A PostgreSQL + pgvector schema with 20+ data-access functions stores vector embeddings and powers retrieval-augmented lookups across newsletter archives, academic papers, and disease/pest trend data.
Make it fault-tolerant
Automated retry logic plus plagiarism, cross-check, and citation-audit gates catch bad output before it ships — reliability engineering, not just model accuracy.
Ship it and keep it running
Deployed via Vite/Railway CI/CD with cron-scheduled production runs — the pipeline ships newsletters on its own schedule, unattended.
More work
Other projects
Turfgrass Newsletter Pipeline
Multi-agent automated weekly newsletter with a fungicide-timing section.
Other Projects
More on GitHub.
Right now
What I’m working on
- Rutgers Turfgrass Pathology LabBuilding the 19-node LangGraph pipeline that runs the lab's newsletter — currently on the fault-tolerance layer (retry logic, plagiarism/citation checks).
- Break Through Tech — Cornell TechAI/ML Fellow, building an income-eligibility classifier on Census data for a CDFI-style lending screen.
- ManuscriptCo-writing up the dollar spot hybrid model results with my professor and a plant-pathology domain expert.
About
Why turfgrass pathology, of all things
I’m a Computer Science and Data Science student at Rutgers. Most of my classmates’ portfolio projects are recommendation engines or chatbots — mine is a disease-outbreak model for golf courses, because that’s the lab that took a chance on a sophomore who could code and wanted to work on something that mattered to a real person’s job. Turf managers make spray/no-spray calls that cost real money and affect real turf; getting them a few days’ more warning turned out to be a genuinely interesting systems problem, not just an ML exercise.
Outside of that, I work across the stack — Python for data/ML, TypeScript and React for interfaces, LangGraph/LangChain when a project needs an actual pipeline instead of a single model call. I like finishing things enough to put them in front of people, which is most of why this site works the way it does.