Available for thoughtful collaborations
Software engineer and researcher working at the intersection of high-performance systems, robotics, and machine learning. I like problems where the theory has to survive contact with real hardware.
Turning natural-language intent into safe, executable behaviour for multi-robot systems.
01 / profile
I am Vedant, a computer scientist who enjoys moving between abstraction levels: from compiler IRs and network silicon to learning systems and the physical world. My work tends to be practical, research-minded, and shaped by a simple question: what would make this robust enough to use?
I graduated from the University of Alberta with a B.Sc. Honors in Computer Science, and I am happiest in teams that value clear thinking, careful experiments, and software that earns its complexity.
02 / experience
A timeline of building, investigating, and teaching.
Arista Networks · Vancouver, BC
Technical University of Munich · Munich, Germany
Arista Networks · Vancouver, BC
Alberta Machine Intelligence Institute · Edmonton, AB
NRC CAN & CCG, University of Alberta · Edmonton, AB
University of Alberta · Edmonton, AB
03 / selected work
Small products, research prototypes, and tools built to be used.
01A meal planning workflow that turns recipes and weekly plans into an automated shopping list.
View on GitHub ↗
02A parser and speech pipeline that turns mathematical notation into natural language and audio.
Open the project ↗
03A playful speech-to-text experiment that surfaces suspicious trigger words in real time.
Open the project ↗
04A command-line data processing tool for searching, updating, and managing a movie database.
View the code ↗04 / research
My research lives where learning systems meet constraints: safe motion, continual adaptation, and tools that make experimentation easier.
Language-based choreography augmented with a safety filter that makes minimal corrections when feasibility constraints are violated.
Read the paper ↗Composing deployable drone choreographies from language and a library of safe motion primitives.
Read the preprint ↗AgarCL, a non-episodic, high-dimensional platform for studying agents that learn in changing environments.
Read the preprint ↗The United Unity Universe, an open-source toolkit for creating varied reinforcement learning environments in Unity.
Read the paper ↗My current line of work explores how expressive, high-level intent can become reliable behaviour in multi-agent systems.
05 / blog
Abstractions work best when they preserve the information the next layer actually needs.
Read note ↗Designing a bridge between expressive instructions and the safety constraints of a drone swarm.
Read note ↗A small argument for showing the questions, constraints, and tradeoffs behind the work.
Read note ↗06 / contact
I am always open to interesting software, research, and collaboration conversations.
vedudx@gmail.com ↗