Joseph Bloom is a Model Transparency Lead in London with five years' experience at the intersection of machine learning, mechanistic interpretability, and computational biology. He has led white-box evaluations of frontier AI systems at the AI Security Institute, co-founded and served as science lead at a research startup, and published proteomics work that produced a novel protein-inference solution. Equally comfortable writing production data pipelines and research code, he blends hands-on engineering (Python/R, Docker, AWS) with academic rigor from a Computational Biology and Mathematical Sciences background. An aspiring effective altruist, Joseph focuses on reducing extreme AI risks through interpretability techniques that probe models' internal states rather than just inputs and outputs. A less obvious thread through his career is a consistent drive to translate deep scientific work into practical, auditable tools and published outcomes.
5 years of coding experience
6 years of employment as a software developer
Masters of Business Analytics - Differed, Masters of Business Analytics - Differed at Melbourne Business School
Post-processing of MaxQuant Label Free Quantification results.
Contributions:31 releases, 100 commits, 56 pushes in 1 year 4 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.