Skip to content
View JakeWeinstein's full-sized avatar
  • Chicago

Block or report JakeWeinstein

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
JakeWeinstein/README.md

Hi, I'm Jake 👋

Applied Math + CS at Northwestern University
Scientific computing · machine learning · quantitative modeling

Resume  Gmail  LinkedIn

I build software at the intersection of numerical methods, machine learning, and quantitative modeling.

  • 🔭 Currently: Dual BS in Applied Mathematics & Computer Science at Northwestern (GPA 3.95), and a Research Assistant in Prof. Niall Mangan's group, building finite-element solvers for stiff nonlinear electrochemical systems.
  • 💼 Summer 2026: Trading Intern at Milliman, developing an ML-based deep-hedging engine for fixed-indexed-annuity liability books — attention networks trained end-to-end over simulated market paths.
  • 🌍 Fall 2025: Computer Science exchange at the University of Edinburgh.
  • 🤝 Open to research and open-source collaboration.

What I work on
PDE solvers & numerical methods Generalizable finite-element solvers for stiff, strongly-coupled nonlinear systems; continuation/homotopy methods for robust nonlinear solves; convergence verified via the method of manufactured solutions.
Scientific machine learning Adjoint gradients for PDE-constrained calibration; neural surrogates; identifiability analysis for mechanism discovery.
Quantitative modeling Deep hedging, attention-based sequence models, stochastic simulation of market paths, model calibration and out-of-sample validation.
AI-augmented research Multi-agent workflows that plan, verify, and harden scientific-computing work — parallel literature review, multi-model correctness checks, and adversarial multi-model critique loops.

Featured projects

Project What it is Stack
PNPInverse A generalizable finite-element solver for the Poisson–Nernst–Planck equations with Butler–Volmer boundary conditions, built to uncover unknown reaction mechanisms. Python, Firedrake
SciAi Multi-agent AI workflows for scientific-computing research — parallel research, multi-model correctness verification, and adversarial GPT critique loops. Python, Claude Code

Toolbox

Languages: Python · C++ · C · Java · MATLAB · SQL ML & scientific computing: PyTorch · Firedrake · finite element methods · PDE-constrained / adjoint optimization · deep learning · attention networks Tools: Claude Code · Git · LaTeX

Applied Math + CS @ Northwestern · graduating June 2027

Pinned Loading

  1. PNPInverse PNPInverse Public

    A generalizable finite-element solver for the Poisson-Nernst-Planck equation with Butler-Volmer boundary conditions.

    Python

  2. SailingViewer SailingViewer Public

    A viewing app used by the Northwestern Sailing team to share practice videos.

    TypeScript

  3. SciAi SciAi Public

    Multi-agent AI workflows for scientific-computing research with Claude Code — parallel literature review, multi-model correctness verification, and adversarial GPT critique loops to plan and harden…

    1