Sanjeew

Hi! I'm Sanjeew Kanagaraj, a Software Engineer currently based in Hong Kong

About Me

My name is Sanjeew and I'm an Engineer from Sri Lanka, currently based in Hong Kong. After graduating from HKU where I majored in Computer Engineering, I worked at Rice Robotics as a Robotics Engineer. I try to apply my knowledge to build cool projects such as NewsCrunch, a website to view summarised daily news from reputable sources - built because of my own need to keep up with the world.

While my experience is primarily in working with AI and hardware systems, I'm open to learning and testing most technologies.


Experience

June 2023 - Present

Rice Robotics

Robotics Engineer
  • Developed multimedia pipelines to enable live video streaming in 4K, recording, two way intercom and deep learning inference using Gstreamer, Python, and Typescript, reducing processing and memory requirements by 80%.
  • Trained and optimized computer vision models to perform various tasks including mask, gate and intruder detection, achieving over 90% accuracy on limited hardware using PyTorch, ONNX and OpenVINO.
  • Improved obstacle avoidance and self docking success rate by implementing a graceful controller for charger detection and docking at firmware level using C++.
April 2021 - March 2023

Robot Data

Software Engineer, Artifiial Intelligence Team
  • Developed computer vison models for real world use cases using Tensorflow and Pytorch, optimized and deployed inference on edge devices using Docker, TensorRT and Nvidia Deepstream SDK.
  • Implemented real time face mask detection in conjunction with temperature checking with precision of over 95%.
  • Setup machine learning pipeline using Kubernetes and Kubeflow to streamline data pre-processing and model creation, improving efficiency by 40%.
Sept 2020 - April 2021

Hanson Robotics

Robotics Intern, Core Engineering Team
  • Co-authored paper titled A Neuro-Symbolic Humanlike Arm Controller for Sophia the Robot, researching the use of Convolution Neural Networks coupled with symbolic AI for object grasping. (Link)
  • Constructed kinematic URDF representation of robotic arms to be used in simulation of intricate movements.Implemented AI behavior tree algorithms to enable complex behavior patterns on Sophia, integrating with the Hanson Robotics SDK.
  • Improved Sophia’s human-robot interaction heuristics and reduced interaction delay by 50%.
June 2020 - Sept 2020

Makerbay

Embedded Computer Vision / Robotics volunteer
  • Worked on the coral reef mapping drone that automates the mapping of coral reefs.
  • In charge of the training and deployment of onboard neural network to classify coral types. Built using Tensorflow and Keras
  • Assisted in modifying electronic components to ensure accurate mapping and stitching of images.
Sept 2019 - June 2020

Quokka Reward

Full Stack Web Developer Intern
  • Worked directly under the CTO as Full Stack developer for the Quokka Rewards platform.
  • Responsible for the development of Django Restful API as well as data analytics to show effectiveness of the platform.
March 2019 - Sept 2019

The University of Hong Kong

Research Assistant
  • Working under Dr. Joe C.H. Yuen on building a cloud-based AI Chabot that helps students learn how to code.
  • Responsible for the full stack construction and deployment of the chatbot analyzing hundreds of student submissions for common mistakes.
  • Worked with Machine Learning, Natural Language Processing, Dialogflow, Microsoft Bot Framework, and Node js.
Dec 2018 – March 2019

The Bangkok Patana School, Bangkok

Robotics Engineer and STEM Educator
  • Demonstrated the workings of a sensory controlled car with Arduino programming and helped students build ones of their own.
Dec 2018 - Jan 2019

Education

University of Hong Kong

Bachelor of Engineering

September 2016 - May 2021

Stafford International School

Cambridge Advanced Level

September 2002 - May 2017

Projects

NewsCrunch

Aggregation and summarisation of daily news using a combination of statistical and deep learning NLP techniques.

Web Scraping Django NLTK

Raytracer

RayTracer buit from scratch in Python

Python Numpy

PointPillarsNet

Implemetation of pointpillars net point cloud object detection on the ZCU 102 FPGA board using VITIS AI

C Pytorch FPGA

RecycleNet

Deep Learning model to classify different types of waste. Built on Keras using transfer learning and fine tuining. Deployed using flask and AWS

Python Pytorch Deep Learning

Tiler

Tile based puzzle game built using C++ and OLCPixelGameEngine

C++

Federated Learning in Robots

Using federated Learning to continously upgrade Face detection and Chatbot models. Tested on the Nao Robot.

Networking Deep Learning NLP

Interests

Some hobbies I currently enjoy are collecting and restoring film cameras, kayaking and talking about why Goodzila is the perfect name for a dog


Awards & Certifications

  • Awarded $48,00 by the Gallant Ho Fund to lead a team of HKU students on an experiential learning trip in the Philippines to test the coral reef mapping drone in partnership with UOP.
  • Funding to conduct research on marine robotics at the HKU Innovation Wing.
  • Selected as mentor for HKU STEM 19.
  • Awarded 1st place at HKU Rube Goldberg machine competition in 2018.
  • Awarded HKU Foundation Scholarship covering tuition upon admission.
  • Awarded HKSAR Government Scholarship.
  • Awarded Outstanding Cambridge Learner Award for Advanced level results in 2017.