8000
Skip to content
View Pulindu1's full-sized avatar
1 follower · 6 following

Achievements

Achievement: YOLOAchievement: QuickdrawAchievement: Pull Shark

Achievements

Achievement: YOLOAchievement: QuickdrawAchievement: Pull Shark

Highlights

  • Pro

Block or report Pulindu1

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Pulindu1/README.md

README

Hi, I'm Pulindu Fonseka

Master of Engineering in Computer Science graduate from Durham University with a background in software engineering at BAE Systems and a strong academic foundation in algorithms and systems optimization.

Connect With Me

Quick Overview

  • Education: MEng Computer Science from Durham University (Upper Second-Class Honours).
  • Experience: Software Engineer at BAE Systems as of Sept 2026.
  • Core Interests: Quantitative finance, high-performance software engineering, and complex algorithmic problem-solving.

Pinned Loading

  1. web-sec-dissertation web-sec-dissertation Public

    Durham MEng dissertation: 9 dockerised web-exploitation CTFs with e2e exploit tests, a 5-model LLM solvability trial, and a human study comparing results.

    Rust

  2. nlp-stance-detection-twitter nlp-stance-detection-twitter Public

    SDQC stance detection on RumourEval 2017 (SemEval-2017 Task 8): n-gram/LDA analysis, BERTweet fine-tuning, FLAN-T5 zero- and few-shot prompting, and a two-stage chain-of-thought cascade, compared u…

    Jupyter Notebook

  3. deep-rl-bipedal-walker deep-rl-bipedal-walker Public

    Reinforcement learning project using Truncated Quantile Critics (TQC) with elite experience replay and observation normalisation to train a Bipedal Walker agent. Includes report, training code, log…

    Jupyter Notebook

  4. procedural-graphics-engine procedural-graphics-engine Public

    Real-time WebGL crowd simulation in pure Three.js — no engine, no build step, no imported models. 3,400+ agents at 60 FPS via instancing, quadtree/spatial-hash partitioning and adaptive LOD. Proce…

    JavaScript

  5. constrained-deep-learning constrained-deep-learning Public

    PyTorch models built under hard budgets: a ResNet hitting 87.7% on AddNIST with <100k params, and a spectrally normalised DCGAN reaching FID 59.95 on CIFAR-100 with <1M params.

    Jupyter Notebook

0