Targeting Aging & Longevity

Decoding Aging with AI & Multi-Omics.

I am Reza Alipour, PharmD, Ph.D. Data Scientist at Meta and Computational Biologist architecting infrastructure to extend human healthspan.

SF Bay Area

The Manifesto

Engineering the Defeat of Aging

Biological aging is a physical engineering problem masquerading as an inevitability. While mind uploading represents the ultimate asymptote of human preservation, solving biological aging is the most feasible and critical engineering challenge of the 21st century.

Combining a PharmD, a Ph.D. in Neuroscience, and expertise in scaling machine learning systems, I am dedicated to dismantling the mechanisms of aging to radically increase human lifespan. My focus is applying AI and multi-omics infrastructure to discover fundamental biological drivers of decline, decode multimodal signatures of aging, and accelerate the transition from theoretical longevity research to clinically viable therapeutics.

15
Peer-Reviewed Papers
125+
Citations
2
Patents
20k+
Startups Analyzed

Technical Stack & Workflows

Computational Biology

  • • Computational Chemistry
  • • Cheminformatics
  • • Functional Genomics
  • • Pharmacogenomics
  • • Target Discovery

Data Science & ML

  • • Python (PyTorch, SciPy)
  • • Graph Neural Networks
  • • Explainable ML Models
  • • Causal Inference
  • • Time Series & A/B Testing

Infrastructure

  • • Docker & Kubernetes
  • • CI/CD Pipeline Design
  • • Distributed Training
  • • Proxmox Environments
  • • Unix/Bash & Git

Product & Strategy

  • • Technical Product Management
  • • Venture Capital Due Diligence
  • • Market Landscaping
  • • Deep-Tech Startup Evaluation
  • • XFN Team Leadership

Professional Experience

Feb 2025 — Present

Data Scientist

Meta | Menlo Park, CA

  • Engineered large-scale ML systems optimizing workflows for 60% of Meta's global revenue.
  • Support 100,000+ active advertisers, driving a 6% increase in targeting precision for the top 1,000.
  • Direct XFN collaboration to scale backend infrastructure and define success metrics.
2023 — Jan 2025

Research Data Scientist

Meta | New York, NY

  • Drove critical insights by analyzing 30,000+ experimental datasets, enabling data-driven design decisions and successfully persuading cross-functional teams to adopt these strategies.
  • Developed ML models for high-dimensional sensor topologies, driving a 150% capacity increase.
2017 — 2023

Graduate Research Assistant

Indiana University | Bloomington, IN

  • Designed and executed large-scale multimodal biological datasets across 600+ subjects.
  • Applied deep learning models to explain and decode the neural dynamics of place cells and time cells in the brain.
  • Worked across multiple frontiers of neuroscience: from optogenetics and multi-electrode array (MEA) recordings to connectomics, complex network analysis, and computational modeling.
2021 — 2022

VC Analyst (Fellow)

IU Ventures | Bloomington, IN

  • Curated and analyzed macro performance datasets covering 20,000+ tech and biotech startups.
  • Conducted rigorous technical due diligence and ML architecture evaluations for a select handful of high-conviction AI and comp-bio platforms.
  • Recommended investments validated by a 4X ROI and secured advisory roles across several deep-tech startups.

Engineering Projects

View all on GitHub
PyTorch Multimodal AI Published

AutoRadAI: ECE Detection Pipeline

An end-to-end, multimodal ensemble AI framework designed to detect extracapsular extension (ECE) in prostate cancer. Fuses MRI, histopathology, and clinical data from 1,001 patients into a unified predictive pipeline.

Utilizes lightweight CNNs engineered for clinical efficiency. Achieved expert-level performance, surpassing human radiologists in real-world testing. (Patented system, Co-author, and Web App Developer).

GNNs Cheminformatics Longevity

Autophagy Flux Score Predictor

Developing a computational framework to predict autophagy flux scores across massive chemical spaces. This pipeline evaluates compounds for their potential to restore cellular proteostasis and clear intracellular debris.

By systematically predicting flux kinetics, this model accelerates the discovery pipeline for novel senolytics and geroprotectors designed to systematically target the biological hallmarks of aging.

Active
LLM Agents Healthcare AI Web App

Dr. Fred: CBT-Powered LLM Agent

Engineered an autonomous virtual mental health companion utilizing Large Language Models grounded strictly in evidence-based Cognitive Behavioral Therapy (CBT) techniques.

Replaces rigid decision trees with dynamic, empathetic NLP. Analyzes user context to deliver actionable psychological strategies (e.g., negative thought challenging, relaxation protocols) accessible 24/7.

2024 App
Python Microservices Full-Stack

AutoDash: Microservice Data Analytics

Developed an automated, microservice-based web application that ingests complex datasets. Reduces manual data-processing effort and allows users to perform dynamic statistical analysis and plotting on the fly.

2023

Education

Ph.D. in Neuroscience

Indiana University, Bloomington, IN | 2017 - 2023

Thesis: Deep Learning for Modeling Neural Dynamics

Doctor of Pharmacy (PharmD)

Shiraz University of Medical Sciences | 2010 - 2016

Top 1% Selectivity

Patents

Holder of two national patents (IR 79812, IR 82494).

These patents cover novel pharmacological formulations, translating molecular biology findings into actionable, targeted therapeutic delivery systems.