Alexandre Sauquet

Hi, I'm

Alexandre Sauquet

CS @ Purdue '27

🇺🇸 USA, CA

I'm is a third year student at Purdue University studying Computer Science, Artificial Intelligence, Statistics, and Mathematics. I'm particularly interested in machine learning and algorithms, with a focus on optimization methods and their real-world applications. I am currently working with Ruizhe Zhang on extending proofs for the Edge of Stability to determine convergence improvements when using momentum. Between research, classes, and internships, I enjoy training my own models and implementing techniques from research papers. I am also involved in ML@Purdue where I oversee project managers and give presentations on SOTA papers in our reading group.

Check out my latest work

A mix of research projects, hackathons, and things I've built for fun. Here are the 3 most recent ones.

Number Expression Solver

Number Expression Solver

A Python solver that exhaustively finds all possible mathematical expressions given a set of numbers to reach a target value. Implements recursive RPN tree generation and multiprocessing to solve puzzles like the '24 game' or Countdown's numbers round.

PythonCombinatorial OptimizationMultiprocessing
Interior Point Linear Programming Solver

Interior Point Linear Programming Solver

A Julia implementation of a primal-dual central path following algorithm for solving linear programming problems. Achieves 7+ digit accuracy on LPnetlib benchmarks, solving problems with 144,000+ non-zero entries in under 300 iterations.

JuliaOptimizationLinear ProgrammingNumerical Methods
Aperture

Aperture

An IOS application to unblur images using a residual-shifting diffusion model with peak signal-to-noise ratio of 29.3 trained on real and synthetic blurring data.

PytorchDiffusion ModelsFlaskImage Processing

Work Experience

  • CAST Software

    CAST Software

    Intern AI

    Integrated CAST Software’s code analysis platform with MCP servers, enabling AI-powered insights from 150+ technologies directly in GitHub Copilot and VS Code. Built APIs and optimized deployment for 44 MCP tools, connecting legacy analysis systems to modern AI agentic assistants and streamlining enterprise implementation by containerizing with Docker.



  • Duarte

    Duarte

    Jr. AI Engineer Intern

    Built AI pipelines using HuggingFace and LlamaIndex for Duarte AI, an empathy and story-driven presentation generator. The system increased production speed by 29% and incorporated multimodal models to analyze user-uploaded content with safety guardrails.



  • Probability Management

    Probability Management

    Intern

    Contributed to development of Excel add-in Monte Carlo simulation tools by testing meta-logistic distribution implementations, conducting validation testing, and creating comprehensive user documentation.

Hire me!