Jared Van Bortel
Software Engineer at Nomic AI
New York, New York, United States
Summary
🤩
Rockstar🎓
Top SchoolJared Van Bortel is a software engineer with 10 years of experience specializing in Python, C++, and machine learning, currently working at Nomic AI in New York. He blends low-level performance work—like CUDA improvements and inference optimizations for llama.cpp—with practical ML tooling, including model conversion pipelines for gpt4all. Jared also contributes to core tensor library robustness in ggml, focusing on build stability, cross-compiler fixes, and code quality. Comfortable across cloud and infra tooling (AWS, Terraform) and production back-ends, he brings a pragmatic eye for performance and deployment. A detail-oriented contributor, he often tackles subtle issues such as null-pointer fixes and build reproducibility that pay off in large open-source ML projects.
10 years of coding experience
Computer Science, Computer Science at Finger Lakes Community College
Github Skills (23)
transformers10
c-language10
gf10
python10
algebra10
gfs10
machine-learning10
build-system10
cmake10
c1110
llm-inference10
c1710
gm10
gpu10
optimisation10
Programming languages (19)
Github contributions (5)
nomic-ai/gpt4all
Sep 2023 - May 2025
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
Role in this project:
Back-end Developer
Back-end DeveloperContributions:29 releases, 351 reviews, 622 PRs in 1 year 8 months
Contributions summary:Jared primarily contributed to conversion scripts, focusing on model conversion to the GGUF format. They worked on cleaning up conversion scripts for different models such as BERT, Replit and MPT, using Python and potentially integrating with Transformers. The changes indicate a strong focus on model format compatibility and optimization for the project's inference needs.
gpt4allllm-inferenceai-chat
ggml-org/llama.cpp
Jun 2023 - May 2025
LLM inference in C/C++
Role in this project:Back-end Developer & DevOps Engineer
Back-end Developer & DevOps EngineerContributions:635 reviews, 212 PRs, 168 pushes in 1 year 11 months
Contributions summary:Jared's commits primarily focus on improving the CUDA implementation for LLM inference within the C/C++ codebase. They addressed a potential null-pointer dereference, ensured GPU compute capability compatibility, and contributed to the code related to the server. Furthermore, the user made changes to the project's build scripts by making scripts executable, and updated the build process. These contributions indicate a focus on performance optimization and infrastructure.
cppllm-inferenceggml
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.