Skip to main content
HimalayasHimalayas logo
Sarthak ShiroleSS
Open to opportunities

Sarthak Shirole

@sarthakshirole

Electrical engineering undergraduate focusing on neuromorphic AI and circuit simulation.

India
Message

What I'm looking for

I seek research or engineering roles combining hardware and AI—neuromorphic, embedded, or circuit-simulation work—at teams valuing experimentation, low-power edge solutions, and mentorship for technical growth.

I am an electrical engineering undergraduate from COEP Technological University with strong academic performance (CGPA 8.9/10, top 5%). I focus on bridging hardware and AI through research in neuromorphic computing and physics-informed machine learning.

My neuromorphic project developed a convolutional spiking neural network using PyTorch and snnTorch, implemented LIF neurons with surrogate gradients, and addressed dead-neuron issues to capture temporal dynamics from event-based vision data.

In scientific machine learning, I built a Physics-Informed Neural Network to accelerate transient circuit simulation, formulating a physics loss based on Kirchhoff’s Voltage Law and validating results against Runge-Kutta solvers with very low error.

I work with Python, C/C++, MATLAB/Simulink, LTSpice and data tools like NumPy, SciPy, PyTorch and visualization platforms. I enjoy reading, music and badminton, and I’m passionate about hardware-software co-design for energy-efficient edge AI.

Experience

Work history, roles, and key accomplishments

IR
Current

Researcher, Scientific Machine Learning

Independent Research

Nov 2025 - Present (7 months)

Developed a physics-informed neural network (Neural-SPICE) to accelerate transient non-linear circuit simulation, achieving a physics residual loss of 5.6e-05 and max current error of 0.0005 A versus Runge-Kutta.

IR
Current

Researcher, Neuromorphic Computing

Independent Research

Nov 2025 - Present (7 months)

Designed and trained a convolutional spiking neural network for event-based gesture recognition, achieving 74.0% Top-1 accuracy and 92.36% sparsity while estimating dynamic energy of 0.0127 μJ per inference on 45nm CMOS benchmarks.

Education

Degrees, certifications, and relevant coursework

CU

COEP Technological University

Bachelor of Technology, Electrical Engineering

2024 -

Grade: 8.9/10.0 (Top 5% of cohort)

Pursuing a Bachelor of Technology in Electrical Engineering with strong academic performance (CGPA: 8.9/10.0, top 5% of cohort).

Tech stack

Software and tools used professionally

Find your dream job

Sign up now and join over 250,000+ remote workers who receive personalized job alerts, curated job matches, and more for free!

Sign up
Himalayas profile for an example user named Frankie Sullivan