Pablo Coto
Design Verification Engineer
California, United States
Summary
🤩
Rockstar🎓
Top SchoolPablo Coto is a Design Verification Engineer with a decade of experience building robust hardware and software validation at Apple and Intel, grounded in an electronics engineering degree from Instituto Tecnológico de Costa Rica and a master’s in Embedded Systems from USI. He blends verification expertise with practical software and cloud skills—contributing to open-source projects that optimize large-scale video analysis and neural network compression, including work integrating OpenVINO and HEVC/ffmpeg into containerized deployments. His background spans hands-on verification, electronic design, and software engineering roles, enabling him to bridge silicon-level validation with ML inference and DevOps workflows. Based in California, he brings a pragmatic, cross-disciplinary approach to making complex systems testable, deployable, and performance-efficient.
10 years of coding experience
8 years of employment as a software developer
Licentiate degree, Electronics Engineering, Licentiate degree, Electronics Engineering at Instituto Tecnológico de Costa RicaMaster's degree, Embedded Systems, Master's degree, Embedded Systems at Università della Svizzera Italiana (USI)
Spanish, English
Github Skills (22)
pytorch10
kubernetes10
docker10
machine-learning10
cloud-infrastructure10
dockers10
openvino10
deeplearning-ai10
deep-learning10
aws10
kubernetes-pods10
compression10
quantization10
object-detection10
loss10
Programming languages (4)
Github contributions (5)
openvinotoolkit/nncf
Mar 2022 - Nov 2022
Neural Network Compression Framework for enhanced OpenVINO™ inference
Role in this project:
ML Engineer
ML EngineerContributions:90 reviews, 20 commits, 22 PRs in 8 months
Contributions summary:Pablo primarily contributed to the implementation of a Neural Network Compression Framework. They focused on object detection and focal loss, specifically modifying and adding code to the examples and losses.py, indicating an involvement in the model training and evaluation. Additionally, the user was involved in the design and implementation of a BootstrapNAS, including the schema and multi-elasticity handlers.
bertsemantic-segmentationmixed-precision-trainingtensorflowclassification
scanner-research/scanner
Jun 2019 - Feb 2020
Efficient video analysis at scale
Role in this project:DevOps Engineer & Cloud Engineer
DevOps Engineer & Cloud EngineerContributions:39 commits, 10 PRs, 8 comments in 8 months
Contributions summary:Pablo's contributions primarily center around infrastructure and deployment configurations within a video analysis project. They implemented and updated dependencies, specifically for video codecs, including HEVC and ffmpeg. Furthermore, the user modified Dockerfiles and build scripts to integrate OpenVINO, a deep learning inference engine, and configured environment variables to enable its use within the project's Docker containers. They also addressed deployment issues in a Kubernetes AWS tutorial.
cpppythonvideo-analysisgpuscale
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.