Malinda Dilhara
Applied Scientist at Amazon Web Services (AWS)
Hillsboro, Oregon, United States
Summary
👤
Senior🎓
Top SchoolMalinda Dilhara is an applied scientist with eight years of experience bridging high-performance distributed systems and machine learning software, now working at AWS after completing doctoral studies. Her background includes building ultra-low-latency trading platforms at LSEG and contributing QA and algorithmic improvements to prominent open-source ML projects like Keras and InsightFace. She brings hands-on expertise in numerical Python optimizations (e.g., migrating to np.linalg.multi_dot) and practical ML engineering for face detection and recognition, showing a blend of performance tuning and model-focused work. Based in Hillsboro, Oregon, she combines academic rigor with production-grade engineering, often improving test coverage and resource management in complex codebases. An under-the-radar strength is her ability to move between core systems engineering and applied ML research, making her effective at shipping reliable, scalable ML systems.
8 years of coding experience
5 years of employment as a software developer
Bachelor of the science of Engineering, Electronic and Telecommunication engineering., Bachelor of the science of Engineering, Electronic and Telecommunication engineering. at University of MoratuwaD.S.Senanayake College, Colombo 07President Collage, Kotte, Sri Lanka.
English, Sinhalese
Github Skills (18)
face-detection10
pytorch10
python10
testing10
numpy10
tensorflow10
diffusion-mri10
face-recognition10
medical-imaging10
machine-learning9
deep-learning9
computer-vision9
pytest8
neural-network8
data-science8
Programming languages (8)
Github contributions (5)
keras-team/keras
Jun 2022 - Aug 2022
Deep Learning for humans
Role in this project:
QA Engineer / Test Automation Engineer
QA Engineer / Test Automation EngineerContributions:11 commits in 1 month
Contributions summary:Malinda's contributions primarily involve modifying and enhancing test files within the `keras` repository. They are focused on updating existing tests, specifically within `keras/utils/layer_utils_test.py` and `keras/utils/text_dataset_test.py`, to ensure proper functionality and address potential merge conflicts. The user appears to be adding, modifying or adjusting tests that evaluate the behavior of different layers, printing summaries, and text datasets. This work suggests a focus on quality assurance and testing within the deep learning framework.
pythondata-sciencedeep-learningneural-networksmachine-learning
dipy/dipy
Jul 2022 - Jul 2022
DIPY is the paragon 3D/4D+ medical imaging library in Python. Contains generic methods for spatial normalization, signal processing, machine learning, statistical analysis and visualization of medical images. Additionally, it contains specialized methods for computational anatomy including diffusion, perfusion and structural imaging.
Role in this project:Back-end Developer
Back-end DeveloperContributions:11 commits in 1 day
Contributions summary:Malinda primarily focused on optimizing and refactoring existing code within the `dipy` library. They consistently replaced instances of matrix multiplications with the `np.linalg.multi_dot` function, likely to improve performance. Their contributions primarily involve changes within modules related to medical imaging reconstruction, including forecast, mapmri, and MSDKI, indicating expertise in the project's core domain. They also corrected formatting issues and addressed a "line too long" error, improving code readability.
signalpythonmicrostructurespatialtractography
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.