Abu Qader is a software engineer with 7 years of experience building and deploying machine learning and production systems, currently focused on model performance at Baseten in New York. He co-founded GliaLab to bring affordable AI-driven medical imaging tools to underserved regions, delivering mammography detection models with near-clinical accuracy. His background spans practical ML in healthcare, insurance, and anti-terror work—ranging from productionizing vision models to building pipelines that reduce bias and false positives. Abu has contributed to popular open-source MLOps tooling (truss) by automating model-serving documentation and templating, smoothing the path from research to production. A Cornell computer science graduate, he combines curiosity about neuroscience with a habit of deliberately stepping outside his comfort zone to learn and iterate quickly. Outside work he enjoys reading, cycling, and exploring how the brain inspires better AI.
7 years of coding experience
4 years of employment as a software developer
Bachelor’s Degree, Computer and Information Science, Bachelor’s Degree, Computer and Information Science at Cornell University
The simplest way to serve AI/ML models in production
Role in this project:
MLOps Engineer
Contributions:118 reviews, 109 commits, 130 PRs in 5 months
Contributions summary:Abu's commits primarily focus on automating and improving the model serving infrastructure for AI/ML models. They added functionality for automatic README generation, which simplifies model documentation and usage instructions. The user refactored code, added documentation links, and implemented templating for generating Truss-specific code snippets, streamlining the model deployment and operational aspects of the `truss` project.
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.
Contributions:3 PRs, 13 pushes, 8 branches in 11 months
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.