Alexander Kristoffersen
Senior Software Engineer at Midjourney
San Francisco, California, United States
Summary
🤩
Rockstar🎓
Top SchoolAlexander Kristoffersen is a Senior Software Engineer based in San Francisco with nine years of experience building computer vision and ML systems, currently contributing to Midjourney. He has deep hands-on expertise in NeRFs and 3D vision from his BERKELEY research and notable open-source work on nerfstudio—refactoring loss metrics, improving forward-pass metrics, and creating datasets and camera optimizations that materially boosted model performance. Prior roles span autonomy and photogrammetry at Skydio, ML research internships at Google and Butterfly Network, and edge-focused vision work at Berkeley RISE Lab, demonstrating a blend of research rigor and production engineering. He combines low-level systems and flight-control experience from high-altitude balloon projects with scalable data plumbing from network-analysis tooling, making him comfortable across the stack from embedded sensors to ML training pipelines. Not obvious from titles: he’s contributed to improving camera extrinsics and dataset tooling that directly enabled higher-quality novel-view synthesis in open-source NeRF workflows.
9 years of coding experience
6 years of employment as a software developer
Master of Science - MS Electrical Engineering and Computer Science (EECS), Master of Science - MS Electrical Engineering and Computer Science (EECS) at University of California, BerkeleyBachelor of Science - BS EECS, Bachelor of Science - BS EECS at UC Berkeley College of Engineering
Github Skills (8)
pytorch10
serf10
deep-learning10
python9
machine-learning9
3d-graphics8
computer-vision8
3d7
Programming languages (4)
Github contributions (5)
nerfstudio-project/nerfstudio
Jul 2022 - Dec 2022
A collaboration friendly studio for NeRFs
Role in this project:
ML Engineer
ML EngineerContributions:45 reviews, 32 commits, 58 PRs in 5 months
Contributions summary:Alexander primarily contributed to the implementation and refinement of loss metrics and model components within the NeRF framework, particularly in the `pyrad` and `nerfactory` subdirectories. They refactored loss calculations, improved the handling of metrics during the forward pass, and addressed scaling issues. Furthermore, the user developed new datasets and optimized camera extrinsics for improved performance within the project.
pytorchphotogrammetrydeep-learningcomputer-vision3d-reconstruction
akristoffersen/akristoffersen.github.io
Nov 2018 - Feb 2025
My personal Website: akristoffersen.com
Contributions:4 PRs, 74 pushes, 5 branches in 6 years 3 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.