Close

ABHISHANK GABA


Proactively Pondering Products





Who Am I?

My name is Abhishank and I Craft Products!

I could waste your time by convincing you that I always " Accomplish X by doing Y leading to Z ", but ultimately, my skills are as temporary as every language I know and as fickle as every tool I use. As temporary as things that will be useless in 10 years. As fickle as things that can be learned by anyone.

The things that LAST are not complete, they are in PROGRESS. So what I will tell you is that I AM IN PROGRESS. I hold on to my methods loosely, embrace flexibility and modularity, am willing to learn, expect to be wrong, and am confident when I am right.

My various internships have given me a chance to dip my toes in a variety of fields. I became a Lean Startup Evangelizer at 1 checkpoint, a Deep Learning Engineer at another, and a Software Connoisseur at the 3rd. My experiences morphed me into a Tech Lover and a Big Data Enthusiast. Feel free to check out what I've been up to by clicking the tabs above.

Experience

Avidbots Corp

Product Manager, Autonomy (Self Driving) Division

As a Product Manager:
  • I evaluate opportunities and determine what gets built and delivered to customers in the autonomous robotics space.
  • This includes me delivering features for localization, path planning, and perception.

Drugless Driving (Impairment Prevention Startup)

Product Manager, Software Lead

As a Product Manager:
  • Transformed a capstone idea into a full fledged company, raising $10,000 and qualifying (finals) for over $65,000 in funding in a span of 16 months.
  • Piloted product lifecycle from idea to end of life: rolling out 3 prototypes, training features like facial recognition, evaluating product performance & iterating on design based on consumer needs.
  • Developed Business Case & Business Model Canvas by researching problem of impaired driving, identifying market opportunity, & defining customer/user requirements.
  • Led Design Phase: defined product vision & strategy for next 3 years, architected firmware/software stack, sought customer feedback, created User Persona Portfolio & built Looks-Like Mock prototype.
  • Headed Engineering Phase - finalized technical specifications, managed construction, conducted end to end Unit and Integration testing to successfully release product.
  • Managed relations with suppliers: 3rd party drug detection companies & direct consumers: public transit, trucking industry. Tracked market trends, industry players & new technologies to develop Unique Value Proposition.

As a Software Lead:
  • Designed and prototyped Raspberry-Pi Testbed with CAN protocol to interface with embedded detectors.
  • Implemented Machine Learning algorithms in Python with facial-recognition for anti-cheat mechanism. Achieved a 99.38% accuracy on the Labeled Faces in the Wild benchmark.

Myant Inc. (Smart Underwear Startup

Hardware & Data Science Intern

  • Worked with a cross functional team to integrate bio-sensing technology into textiles. Conducted end-to-end testing.
  • Found a 86% correlation between Skin Temperature and cancer markers by building a Linear Regression Machine Learning Model.

CBC Canada

QA Analyst Intern for Desktop & Mobile Site

  • Worked with internal development team & product stakeholders (Journalists) to define: user needs, feature specs, product performance, feasibility, scope, & development time.
  • Performed analysis on CBC's Desktop & Mobile sites. Conducted end-to-end testing (JSON, HTML, editor) to release new features.
  • Self initiated: Standardized testing protocols, developed training materials & conducted product training sessions for Functional QA team, increasing efficiency by 25% and introducing a matrix structure.
  • Self-Initiated: found root cause of CBC website crashes (cache limit exceeded) on Nokia Phones, resolving urgent issue raised by Senior personnel at Microsoft.

Advantex Marketing (CIBC Rewards Accelerator)

Software Development Intern

  • Scoped, wrote & released a diagnostic tool for server crashes, report hangs, and data corruptions by logging report data based on a primary key. Saved developer’s 8 hours of weekly troubleshooting in an agile environment.
  • Automated company’s financial statement by implementing Hashmap ADT in Eclipse to replace Excel’s Vlookup. Reduced execution time by 33% & made consumer risk management easier for CFO.
  • Wrote & unit tested Java Data Services (ETL): integrated SQL for data extraction from MySQL relational databases using OOP methodology. Improved finance team’s efficiency by 20%.

Education

University of Waterloo

May, 2019

BASc. in Mechatronics Engineering (Management Science Option) with Distinction,
GPA: 4.0 (3rd & 4th Year)

Relevant Management/Entrepreneurship Courses


Relevant "AI/Cloud Computing" Courses

Projects

Research paper: Automated Sewer Inspection - Present

This is a research paper I worked on over the past year with 1 other author. We are actively iterating on the paper's implementation of detecting defects in sewer pipes, in order to get it published. The abstract is given below.

A deep multi-class convolutional neural network is built to detect critical points in pipes; specifically joints, connections, and manholes. An accuracy of 91.7% is achieved using a dataset composed of 7 pipe videos. Three hyperparameters are varied: learning rate, batch size, and class weights assess their impact on training. In sum, the high accuracy implies that the model may be overfitted to the given dataset, despite the data augmentations, 5 fold validations, and dropouts used.

View Project

Indoor Route Guidance for the Blind (Matlab) - November 2018 - April 2019

I, along with 1 other partner, determined person's current location using an Extended Kalman Filter. I, then, calculated the shortest path to their final location using the A* algorithm (variant of Dijkstra's Algorithm).

View Project

Kaggle Challenge: Primary Site Classification (Google Collaboratory, Python) February 2019- April 2019

I identified different tissue patterns from different primary sites (lung, kidney, and ovary) by building a convolutional neural network using a Keras Sequential Model (Machine Learning), leading to an accuracy of 80.20% on unseen test data.

Implementation details are provided in the pdf file located in the github repository. File name: "Implementation_Explanation.pdf"

View Project

Activity Classifier (Python) – August 2018

This was the first machine learning personal project I ever tried. I completed this project over the summer of 2018.

I Calculated statistical features (mean, standard deviation, etc) by filtering, signal processing, and spectrally analyzing IMU data from 6 subjects.

I then built a MICD classifier (Machine Learning) to identify whether person is walking, running, sitting, or cycling.

View Project

Skills

I take pride in my multifaceted approach to crafting simple products that leave an impact on the consumer.

I love making new friends. Feel free to say HELLO!

hit counter