Adrian Gonzalez
London, England, United Kingdom
Summary
🤩
Rockstar🎓
Top SchoolAdrian Gonzalez is an experienced software engineer with 11 years in backend and MLOps work, based in London. He has contributed to prominent open-source ML serving projects like KServe, MLServer and Seldon Core, adding MLServer support for SKLearn/XGBoost, V2 protocol implementations, gRPC endpoints and e2e tests to improve production readiness. Comfortable across Python, gRPC and Kubernetes environments, he combines hands-on development with DevOps sensibilities to ship reliable inference infrastructure. A fast learner and steady problem-solver, Adrian brings leadership and strong teamwork to complex platform projects. His background in computer engineering and sustained open-source contributions show a pragmatic focus on making ML model deployment more robust and maintainable.
11 years of coding experience
Engineer's Degree, Computer Engineering, Computer Engineering, Engineer's Degree, Computer Engineering, Computer Engineering at Universitat d'AlacantMsSc Software Enginneering, Computer Software Engineering, MsSc Software Enginneering, Computer Software Engineering at UA - Universidad de Alicante / Universitat d'Alacant
French, Spanish, English
Stackoverflow
56reputation
1kreached
5answers
0questions
Github Skills (25)
kubernetes10
xgboost10
back-end-development10
python10
protocol-buffers10
scikit10
machine-learning10
java10
javas10
mlops10
kubernetes-pods10
spring-boot10
scikit-learn10
backend10
grpc10
Programming languages (16)
Github contributions (5)
SeldonIO/MLServer
Jun 2020 - Jan 2023
An inference server for your machine learning models, including support for multiple frameworks, multi-model serving and more
Role in this project:
Backend Engineer
Backend EngineerContributions:3 releases, 406 reviews, 789 commits in 2 years 8 months
Contributions summary:Adrian's commits focused on implementing the foundational components of an inference server, primarily through Python and gRPC. They were involved in setting up the initial file structure and generation of protocol buffer files necessary for the server's gRPC interface. Additionally, the user initiated the implementation of core functionalities by starting to work on request handlers and implementing the necessary gRPC endpoints.
inferencemachine-learning-modelsmachine-learningscikit-learnxgboost
kserve/kserve
Nov 2020 - Dec 2021
Standardized Distributed Generative and Predictive AI Inference Platform for Scalable, Multi-Framework Deployment on Kubernetes
Role in this project:MLOps Engineer
MLOps EngineerContributions:10 reviews, 6 commits, 6 PRs in 1 year 1 month
Contributions summary:Adrian primarily contributed to the development and enhancement of the KServe platform, specifically adding support for MLServer within the SKLearn and XGBoost predictors. This included implementing V2 protocol support and integrating the MLServer framework, improving the platform's ability to serve models. The user also added e2e tests for MMS with the V2 protocol to ensure reliability and maintainability. Finally, the user updated the code for more modern dependencies like MLServer 0.5.3.
aiinferencekubernetesknativemachine-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.