Curriculum Vitae

Experience

Machine Learning Researcher (PhD Candidate) Sep 2022 – Present

Muller Lab, Western University & Fields Lab for Network Computation, Fields Institute · Toronto, ON

Developed S¹, a fully interpretable state-space model achieving strong sequence-modeling performance with full auditability and end-to-end tractability.
Created a mathematical framework to analyze latent representations in sequence models (S4, Mamba), optimizing for long-range dependencies in time-series data.
Developed inference-time spectral control methods to dynamically steer generation in Mamba-based LLMs.

Graduate Teaching Assistant Sep 2022 – Present

University of Western Ontario · London, ON

Taught and mentored 150+ students in advanced mathematics — linear algebra, calculus, ODEs/PDEs, and mathematical modeling — translating theoretical concepts into practical problem-solving.

Associate Strategy Consultant Mar 2022 – Sep 2022

Curinos · Toronto, ON

Advised Big Five Canadian and major US banks on modernizing retail checking suites and defining competitive value propositions across $250B+ in deposits.
Developed a new advisory product adopted by 15+ regional banks and fintechs — a scalable, data-driven framework to modernize checking and savings portfolios.
Translated complex financial data into executive-ready insights, informing C-suite pricing strategies across $50B+ product portfolios.

PhD in Applied Mathematics Sep 2022 – Aug 2026 (expected)

University of Western Ontario · London, ON

GPA 4.0 / 4.0 · Focus: neural sequence models, mechanistic interpretability, inference-time interventions · Supervisors: L. E. Muller & J. Mináč

M.A. in Pure Mathematics Sep 2020 – Aug 2021

York University · Toronto, ON

GPA 8.13 / 9.0

HBSc, Specialist in Mathematics Sep 2015 – Aug 2019

University of Toronto · Toronto, ON

GPA 3.86 / 4.0

Explicit operator explains end-to-end computation in the modern neural networks used for sequence and language modeling

Shikder, A. N., et al.

Under review · Physical Review X

arXiv →

S¹: A Precisely Interpretable State Space Model via an End-to-End Closed-Form Oscillatory Operator

Dey, R.* and Shikder, A. N.*, et al. (* equal contribution)

Under review · NeurIPS

Exact expression for maximum Lyapunov exponent during transient dynamics in networks with expressive computational capabilities

Powanwe, A.*, Liboni, L.*, Shikder, A. N., et al.

Under review · Physical Review Letters

arXiv →

Complex Walks for Interpretable Associative Memory in State-Space Networks

Shikder, A. N., et al.

In preparation

Languages & ML PythonPyTorchLangChainHugging FaceNumPy

Modeling Sequence ModelsRepresentation LearningInterpretability

Tools GitSlurmMATLAB