Adonai Vera
Computer Vision Engineer at Voxel51
Cincinnati, Ohio, United States
Summary
🤩
RockstarAdonai Vera is a Computer Vision Engineer based in Cincinnati with seven years of hands-on experience building and integrating ML models for real-world visual AI systems. He contributes to prominent open-source projects like FiftyOne and Supervision, where he implemented model integration, tokenizer and architecture adjustments, and robust CSV serialization and testing for detection data. Comfortable across model deployment, dataset refinement, and backend test automation, he has practical experience streamlining model loading and handling input-size issues for diverse architectures including Yolo-NAS. Equally at home fine-tuning algorithms and hardening data pipelines, he brings a pragmatic focus on reproducible tooling and maintainable code. Outside of code, he pursues high-adrenaline hobbies like skydiving and scuba diving, reflecting a taste for disciplined risk-taking that informs his engineering approach.
7 years of coding experience
English, Spanish
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (15)
continuous-deployment10
object-detection10
computer-vision10
pytorch10
machine-learning10
csv10
integrate10
pytest10
python10
integrations10
data-integration10
ml-deployment10
testing10
data-science9
tensorflow8
Programming languages (5)
Github contributions (5)
roboflow/supervision
Jan 2024 - Mar 2024
We write your reusable computer vision tools. 💜
Role in this project:
Back-end Developer & Test Automation Engineer
Back-end Developer & Test Automation EngineerContributions:11 reviews, 9 PRs, 29 comments in 1 month
Contributions summary:Adonai focused on implementing and testing a CSV serialization feature for the `supervision` library, specifically targeting the `Detections` object. They developed a `CSVSink` class to facilitate saving detection data into a CSV file. Furthermore, the user implemented and tested the functionality within the `test_csv.py` and `test/detection/test_csv.py` files, ensuring the correct writing and reading of CSV data. The user also refactored the test methods.
classificationcococomputer-visiondeep-learningimage-processing
voxel51/fiftyone
Dec 2023 - Mar 2024
Refine high-quality datasets and visual AI models
Role in this project:ML Engineer
ML EngineerContributions:4 reviews, 5 PRs, 12 comments in 2 months
Contributions summary:Adonai's contributions primarily focused on integrating and modifying machine-learning models within the FiftyOne framework. They made changes related to tokenizers, model architectures, and dataset integration for the open-clip and super_gradients libraries, demonstrating a deep understanding of model deployment and data handling. The user also addressed input size issues and refactored existing code, streamlining the model loading process. Their work included adjustments to the codebase to work with various models such as Yolo-NAS.
pytorchpythonvisiondata-sciencedeep-learning
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.