About

ML & Software Engineer

Graduating May 2026

I build ML systems, full-stack applications, and on-device inference pipelines. Current focus: edge AI optimization - quantization, model compression, and low-latency inference on mobile and embedded devices. Beyond that, I'm at the gym, reading, or building side projects.

Machine LearningFull-StackEdge AI
Madison, WI & Nashville, TN
Currently

BS of Computer Science & Data Science @ UW-Madison

Machine Learning Intern (Capstone) @ Qualcomm

Machine Learning Assistant @ Space Science Engineering Center

Background

Engineering in Production

My skills and journey — academic and professional.

Experience

  • Machine Learning Intern (Capstone)

    Qualcomm · Madison, WI

    Jan 2026Present

    Edge AI · On-Device Inference · Model Quantization · Mobile Systems

    • Architected real-time multimodal inference pipelines on Android NPUs using hardware-aware quantization and pruning.
  • ML Research Assistant

    UW-Madison SSEC · Madison, WI

    Sep 2025Present

    Computer Vision · ML Infrastructure · Geospatial AI

    • Engineered high-throughput optical flow pipelines to extract 3D atmospheric vectors from satellite imagery.
  • Software Engineering Intern

    Techbaton · Remote

    May 2025Aug 2025

    Generative AI · Full-Stack ML · Microservices · LLM Orchestration

    • Deployed a GenAI-powered learning platform integrating Llama 3 agents with scalable microservice architecture.
  • Software Engineering Intern

    Boys & Girls Clubs of Middle Tennessee · Nashville, TN

    May 2024Jul 2024

    Mobile Engineering · Technical Leadership · iOS

    • Directed mobile development bootcamps and designed technical curriculum for 150+ students.
  • Research Intern

    Vanderbilt University Medical Center · Nashville, TN

    May 2022Jul 2022

    Statistical Modeling · Data Science · Data Visualization · Algorithm Design

    • Developed statistical software packages to automate high-dimensional drug toxicity and synergy validation.

Education

  • BS in Computer Science and Data Science

    University of Wisconsin-Madison · Madison, WI

    Aug 2023May 2026

    • Coursework: AI, ML Theory, Data Science Algorithms, Statistical Modeling, Probability Theory, Big Data Systems, Database Systems, Advanced DSA, Software Engineering, Systems Programming (OS, Hardware, Networks)
    • Activities: Wisconsin AI Safety Initiative, Tech Exploration Lab

Projects

Personal Works

Projects, hackathon demos, and open-source.

PT

Prompt Tuner

Cloud-based prompt optimizers send private data to external servers. Static libraries break with updates.

A Chrome extension that acts as a 'Grammarly for Prompts', optimizing chat inputs entirely on-device using Gemini Nano.

Impact: Built a fully offline optimizer that intercepts text directly from the browser DOM and tunes prompts dynamically.

Generative AIEdge AIFull-StackRepo

Janus

Standard audio codecs fail below 6kbps, making satellite calls expensive and unintelligible in remote areas.

A 'Semantic Codec' that transmits meaning and tone rather than raw audio, using AI to rebuild voices over weak connections.

Impact: Achieved natural voice calls at just 300 bps, reducing satellite bandwidth costs while keeping vocal emotion intact.

Generative AIEdge AISystemsHackathonRepo
CC

CardinalCast

I wanted to build an end-to-end ML application to practice real-time data ingestion and job scheduling.

A weather prediction market where users place virtual bets on daily forecasts using ML-generated odds.

Impact: Built a daily NOAA data pipeline and a custom probability model that automatically resolves bets and updates wallets.

Machine LearningData EngineeringFull-StackRepo

Blog

Writing & Notes

Posts, announcements, and deep dives.

Read Risk Pricing Weather with Quantile Regression
4 min read

Risk Pricing Weather with Quantile Regression

I built the ML pipeline for a weather prediction market as part of a team project (CS 506). Teammates handled the Java backend and React frontend; I built the Python ML components: models that generate risk-adjusted odds for weather outcomes. The wo

Machine LearningXGBoostProduction ML+1
Read

Contact

Feel Free to Reach Out

Always open to collab or discussing new opportunities. Check out my socials.

© 2026 Akshat Vasisht. All rights reserved.