Skip to main content
ML & Software EngineerAkshat Vasisht

About

ML & Software Engineer

Graduating May 2026

Akshat Vasisht
Resume

I build ML systems, full-stack applications, and production inference pipelines. Current focus: on-device quantization for edge deployment and deterministic orchestration of multi-agent coding workflows. Outside of work: gym, reading, side projects.

MLFull-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

Experience & Education

Work history, coursework, and technical skills.

Experience

  • Machine Learning Intern (Capstone)

    Jan 2026 — Present

    Qualcomm · Madison, WI

    Edge AI · Model Quantization · On-Device Inference

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

  • ML Research Assistant

    Sep 2025 — Present

    UW-Madison SSEC · Madison, WI

    Computer Vision · ML Infrastructure · Geospatial AI

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

  • Software Engineering Intern

    May 2025 — Aug 2025

    Techbaton · Remote

    Generative AI · LLM Orchestration · Microservices

    • Deployed a learning platform integrating Llama 3 agents with microservice architecture.

  • Software Engineering Intern

    May 2024 — Jul 2024

    Boys & Girls Clubs of Middle Tennessee · Nashville, TN

    Technical Leadership · Mobile Engineering

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

  • Research Intern

    May 2022 — Jul 2022

    Vanderbilt University Medical Center · Nashville, TN

    Statistical Modeling · Data Science · Scientific Computing

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

Education

  • BS in Computer Science & Data Science

    Aug 2023 — May 2026

    University of Wisconsin-Madison · Madison, WI

    • 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

Oracle Cloud Infrastructure

AI FoundationsData Science ProfessionalGenerative AI Professional

Projects

Selected Projects

Projects, hackathon demos, and open-source.

View All Projects

Sigil

Coding agents produce inconsistent results. Chaining them requires fragile scripts with no recovery.

A CLI that orchestrates coding agents as deterministic directed graphs. Validation gates enforce quality between steps, and checkpoints enable crash recovery.

Reproducible, resumable runs. Visual editor to compose and monitor agent workflows in real time.

Generative AIDevToolsSystems
Repo

Janus

Audio codecs bottom out around 6 kbps. Below that, low-bandwidth calls degrade into unusable noise.

A real-time codec that transmits speech as text and pitch data instead of waveforms, hitting 300 bps. Reconstructs natural audio preserving speaker identity via generative TTS.

20x below Opus minimum. Fully local inference, no cloud dependency. 158x satellite cost reduction.

Generative AIEdge AISystemsHackathon
Repo

CardinalCast

End-to-end ML class project covering real-time data ingestion, job scheduling, and automated payouts.

A weather wagering platform that prices bets using a calibrated probability model. A daily pipeline resolves wagers against NOAA actuals and refreshes odds.

Sub-100ms pricing. House edge held at 5-7% through calibrated probability models.

MLData EngineeringFull-Stack
Repo

Blog

Writing

Technical posts on ML and engineering decisions.

View All Posts
Read Quantile Regression for Weather Risk Pricing
2 min read

Quantile Regression for Weather Risk Pricing

I built the ML components for a weather prediction market (CS 506 team project): models that generate risk-adjusted odds for temperature, wind speed, and precipitation outcomes. Ensembles require uncorrelated errors I started with an averaging ense

MLData Engineering
Read

Contact

Reach Out

Happy to chat about opportunities, research, or interesting projects.

© 2026 Akshat Vasisht. All rights reserved.