About

Software Engineer with 2.5+ years building production AI/ML and backend systems in Python, Jac, and Go: LLM-powered agentic applications, MLOps pipelines, and scalable infrastructure. Shipped AI products used by real customers, including live apps on Google Play and the App Store. Open-source core contributor to the Jaseci stack and co-author of two IEEE-published papers on deep learning.

Experience

  1. AI/ML Engineer · Jaseci Lab

    Apr 2024 – Present

    Ann Arbor, MI, USA · Remote

    • Core contributor to the open-source Jaseci stack (950+ GitHub stars) with 70+ merged PRs, as a core developer of the jac-scale Kubernetes deployment and scaling features and contributor to the jaclang language.
    • Developed and maintained backend infrastructure for Tobu, an AI-powered personal memory platform with integrated LLMs serving 1,000+ users; took the system to production fast enough to support the company's $1.5M raise.
    • Shipped ML features for image analysis and conversation processing that turn unstructured photos and chats into structured, searchable information, and built scalable PySpark pipelines for user analysis and feature optimization.
    • Lead developer of Flowline, an AI-powered project management platform deployed on Kubernetes, and built the Veo 3 image-to-video pipeline behind TLite, live on the App Store.
    PythonJacKubernetesLLMsPySparkFastAPI
  2. Data Scientist · Utech Technologies (Pvt) Ltd

    Apr 2024 – Jun 2024

    Wattala, Sri Lanka · Remote

    • Designed and deployed an end-to-end energy forecasting pipeline with MLflow experiment tracking and model versioning for reproducible, production-ready forecasts.
    • Automated ML workflows with Apache Airflow for data ingestion, model retraining, and deployment.
    • Built production API services with FastAPI and Docker for real-time energy prediction and dashboard visualization.
    MLflowApache AirflowFastAPIDockerPython
  3. Application Engineer Intern · Synopsys Lanka (Pvt) Ltd

    Jan 2023 – Jul 2023

    Colombo, Sri Lanka · On-site

    • Developed an NLP-based search engine with LSTM models for automated email classification.
    • Automated large-file compilation and notification systems using Python, Bash, and CSH scripting.
    • Managed 17 processor designs through custom automation scripts for daily performance assessment and resource optimization.
    PythonBashLSTMNLP

Education

B.Sc. Engineering (Hons) in Electrical Engineering

University of Moratuwa · Jan 2020 – Jul 2024

GPA 3.31 (Second Upper Class) · Washington Accord-accredited · Dean's List (Semester 2)

Skills & technologies

Toolbox

Languages

  • Python
  • Go
  • Rust
  • TypeScript
  • Jac (jaclang)
  • SQL
  • Bash

AI & GenAI

  • LLMs
  • RAG
  • Agentic AI
  • LangGraph
  • Fine-tuning (Unsloth)
  • NLP
  • Deep Learning
  • Veo 3

ML Frameworks

  • PyTorch
  • TensorFlow / Keras
  • scikit-learn
  • Hugging Face

MLOps & Infra

  • Docker
  • Kubernetes
  • MLflow
  • Apache Airflow
  • CI/CD (GitHub Actions)
  • Google Cloud
  • AWS

Backend & Data

  • FastAPI
  • Jaseci
  • PostgreSQL
  • PySpark
  • Kafka
  • Redis Streams
  • WebSockets
  • Chroma

Publications

Peer-reviewed work on self-adaptive deep learning for non-intrusive load monitoring.

Research

2024 IEEE World AI IoT Congress · 2024

Self-Adaptive Non-Intrusive Load Monitoring Using Deep Learning

M. S. K. Nisakya, S. M. L. Arampola, W. A. Yasodya, S. Kumarawadu, V. Logeeshan, C. Wanigasekara

Introduces a self-adaptive NILM model integrating deep learning with transfer learning and pseudo-labeling, so energy-monitoring models keep working as appliance power patterns drift with age.

Best Presented Paper Award

IEEE Access, vol. 13, pp. 106524–106539 · 2025

Self-Adaptive Deep Learning Framework for Non-Intrusive Load Monitoring: Addressing Aging Appliance Challenges With Transfer Learning and Pseudo Labeling

W. A. Yasodya, S. M. L. Arampola, M. S. K. Nisakya, V. Logeeshan, S. Kumarawadu, C. Wanigasekara

Journal extension of the self-adaptive NILM framework, with synthetic data generation and advanced neural architectures achieving high disaggregation accuracy on aging appliances.

GitHub activity, live

Fetched from the GitHub GraphQL API and revalidated hourly. These are not hand-typed numbers.

By the numbers

Live from the GitHub API

2,283

Contributions

past 12 months

3,104

Commits

all-time

406

Pull Requests

all-time

29

Public Repos

on GitHub

2

IEEE Publications

peer-reviewed

2.5+

Years of Experience

and counting

Last 12 months of GitHub contributions: 2,283 total

Let's build something intelligent.

Open to AI/ML engineering roles, freelance projects, and research collaborations. The fastest way to reach me is email. I usually reply within a day.

+94 77 271 5351 Sri Lanka · Remote worldwide