Benjamin Sherman
Machine Learning Engineer at Weights & Biases
San Francisco, California, United States
Summary
🤩
Rockstar🎓
Top SchoolBen Sherman is a Software Engineer in San Francisco with a decade of experience and doctoral training in Computer Science from MIT focused on probabilistic programming and verified computation with continuous values. He brings research-grade expertise in statistical machine learning, perception, prediction, and trustworthy AI to production systems at Waymo. An active contributor to AI developer tooling, he implemented back-end and DevOps enhancements to the widely used wandb/wandb project—adding Git integration, launch infrastructure, Kubernetes object support, and base-image/runtime dependency management so jobs can be launched from existing images. Ben blends rigorous mathematical training (BS in Mathematics from Yale) with hands-on systems engineering, uniquely bridging auditable verification research and scalable ML infrastructure. He’s especially drawn to statistical approaches that make perception and prediction both accurate and interpretable.
10 years of coding experience
3 years of employment as a software developer
University of California Santa Cruz
Github Skills (11)
kubernetes-pod10
kubernetes10
dockerce10
docker10
python10
dockers10
ci-cd9
git9
kaniko8
gcp8
aws8
Programming languages (7)
Github contributions (5)
wandb/wandb
Jul 2022 - Jan 2023
The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.
Role in this project:
Back-end & DevOps Engineer
Back-end & DevOps EngineerContributions:2 releases, 320 reviews, 63 commits in 6 months
Contributions summary:Benjamin implemented several enhancements to the Weights & Biases platform, focusing on the Git integration and launch features. They added functionality to specify a custom root directory for Git repositories using settings or environment variables, along with code to manage and install dependencies. The user also worked on the launch infrastructure, introducing environment and registry classes, supporting custom Kubernetes object deployments and addressing issues related to the base image support for a better developer experience. The user implemented a base image and environment settings so jobs can be launched from existing images.
pythoncollaborationtensorflowhyperparameter-tuningcli
bcsherma/superres
May 2022 - Jul 2022
Contributions:42 commits, 22 pushes in 2 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.