CV

You can downlaod a pdf of my CV above.

Basics

Name Ram Eshwar Kaundinya
Role Neuromoprhic AI Researcher and AI Engineer
Email r.e.kaundinya@rug.nl
Url https://rkaundinya.github.io
Summary PhD Candidate at the University of Groningen researching neuromorphic computing for tactile and sensorimotor applications. Strong interest in cognitive architectures, dynamical systems theory, control theory, cognitive science, and philosophy. A veteran video game engineer working alongside renowned developers from Call of Duty, World of Warcraft, LEGO, Civilization, XCom, Skyrim, the Sims, and more.

Work

  • 2024.09 - 2029.03
    PhD Candidate at Cognigron
    University of Groningen
    I work at the intersection of neuromorphic computing, artificial intelligence, cognitive science, dynamical systems, and control theory. I am a part of the Cognigron center and the NWO funded NL-ECO project. I have a particular interest in the application of dynamic reconstructive memory architectures for real-time sensorimotor control tasks. I am also interested in embodied AI and the applications of self-organizing systems to building intelligence from the ground up. I am interested in the intersection of relevance realization and dynamical systems theory.
  • 2024.03 - 2025.07
    Gameplay Engineer
    Midsummer Studios
    I worked as an engineer at Midsummer Studios founded by Jake Solomon, Will Miller, and Nelsie Birch on a life simulation game. My work remains confidential, but involved elements of implementing novel artificial intelligence pipelines, cloud engineering, telemetry, and edge compute optimizations.

Education

Awards

  • 2024.03
    Honors Society
    Upsilon Pi Epsilon
    Honors Society award for excellence in the field of computer science awarded at Drexel University for my masters work.

Certificates

Publications

  • 2025.07.08
    Biologically-Inspired Representations for Adpative Control with Spatial Semantic Pointers
    IEEE
    We explore and evaluate biologically-inspired representations for an adaptive controller using Spatial Semantic Pointers (SSPs). Specifically, we show our method for place-cell-like SSP representations outperforms past methods. Using this representation, we efficiently learn the dynamics of a given plant over its state space. We implement this adaptive controller in a spiking neural network along with a classical sliding mode controller and prove the stability of the overall system despite non-linear plant dynamics. We then simulate the controller on a 3-link arm and demonstrate that the proposed representational method gives a simpler and more systematic way of designing the neural representation of the state space. Compared to previous methods, we show an increase of 1.23-1.25x in tracking accuracy.

Skills

Languages and Frameworks
Python
C
C++
C#
Java
Unreal Engine
Unity
Nengo
SNNTorch
PyTorch
ACT-R
Docker
Topic Areas
Neural Networks
Reinforcement Learning
Neuromorphic Computing
Artificial Intelligence
Cognitive Science
Dynamical Systems
Control Theory
Game Development

Languages

English
Native speaker
Telugu
Conversational
Spanish
Basic

Interests

Philospohy
Neoplatonism
Vedanta
Mysticism
Alfred North Whitehead
Spinoza
Alan Watts
Jiddu Krishnamurti
Aristotle
Plato
Socrates
John Vervaeke
Engineering
Thousand Brains Theory
Dynamical Systems
Control Theory
Reinforcement Learning
Neural Networks
Neuromorphic Computing
Robotics