Praneet Vibhu B.

Software Engineer

New York, New York, United States6 yrs 3 mos experience

Most Likely To SwitchHighly Stable

Key Highlights

Expert in CMOS chip design and FPGA implementation.
Proficient in machine learning and neural network applications.
Strong background in computational neuroscience and systems biology.

Stackforce AI infers this person is a Hardware and Software Engineer specializing in semiconductor and AI technologies.

Contact

Skills

Core Skills

Software DevelopmentHardware DesignMachine Learning

Other Skills

JavaCMOS chip designCadence VirtuosoFPGAConvolutional Neural NetworksSpike Time Dependent PlasticityComputer ArchitecturePythonVHDLResearchMatlabC++HTMLRNeural Networks

About

I aim to build hardware and systems based on neurocomputing. I have worked on CMOS chip design as well as System-on-chip (SoC) platforms. I have taken multiple courses involving machine learning and neural networks during my undergraduate and graduate courses of study. I have studied computational neuroscience and systems biology as well to further understand the functioning of the system which influenced neural networks, the Brain.

Experience

Amazon

SDE

Aug 2022 – Present · 3 yrs 7 mos · New York, United States

JavaSoftware Development

Capital one

Data Engineer/Python Developer - Contractor

May 2020 – Sep 2022 · 2 yrs 4 mos

Columbia university in the city of new york

2 roles

Research Assistant

Sep 2019 – Dec 2019 · 3 mos

Dense CMOS Chip Design, Lightwave Research Laboratory:
Designed a CMOS chip (TSMC 180nm technology) to drive a large optical phased array using Cadence Virtuoso
Designed the layout of the memory block and pad frame, and ran DRC, LVS, ERC and Antenna checks on the whole chip
Implemented a control block on a Cyclone IV FPGA to drive the digital inputs to the chip

CMOS chip designCadence VirtuosoFPGAHardware Design

Summer Research Assistant

May 2019 – Sep 2019 · 4 mos

Neural Acoustics Processing Lab:
Designed a feedforward Convolutional Spiking Neural Network for spoken digit recognition from TIDIGITS dataset
Applied a novel training method based on Spike Time Dependent Plasticity (STDP) synapse updates achieving 95% accuracy

Convolutional Neural NetworksSpike Time Dependent PlasticityMachine Learning