neuwirth/levineuwirth.org
neuwirth
/
levineuwirth.org
1
1
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

auto: 2026-09-03T11:41:27Z [skip ci]

This commit is contained in:
Levi Neuwirth 2026-09-03 13:41:27 +02:00
parent 8023c3679d
commit 7f3ffc7ebe
No known key found for this signature in database
2 changed files with 6 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
content/about.md
View File

@ -2,6 +2,7 @@
title: Levi Neuwirth — Vita title: Levi Neuwirth — Vita
tags: meta tags: meta
history: history:
- date: "2026-09-03"
- date: "2026-08-11" - date: "2026-08-11"
- date: "2026-08-10" - date: "2026-08-10"
- date: "2026-07-25" - date: "2026-07-25"
@ -19,7 +20,7 @@ The formal record. For a less formal, more detailed introduction to who I am, se
## Documents ## Documents
- **[Curriculum Vitae (PDF)](/cv.pdf)** — the complete record, including grants, affiliations, languages, and technical skills. - **[Curriculum Vitae (PDF)](/cv.pdf)** — the complete academic and research record, including publications, presentations, grants, affiliations, projects, and technical skills.
- **[Resume (PDF)](/resume.pdf)** — one page, engineering-facing. - **[Resume (PDF)](/resume.pdf)** — one page, engineering-facing.
- **[Project index](/cv/projects/)** — engineering artifacts in depth, with links to writeups and source. - **[Project index](/cv/projects/)** — engineering artifacts in depth, with links to writeups and source.
@ -32,6 +33,6 @@ My work clusters into four threads:
- **AI safety and applied AI** — zero-knowledge proofs for cryptographic verification of large language models, as a MARS V fellow with the [Cambridge AI Safety Hub](https://caish.org/mars) (mentored by James Petrie, Future of Life Institute); a Magic: The Gathering reinforcement-learning project; and reasoning, evaluation, and red-teaming research contracts. - **AI safety and applied AI** — zero-knowledge proofs for cryptographic verification of large language models, as a MARS V fellow with the [Cambridge AI Safety Hub](https://caish.org/mars) (mentored by James Petrie, Future of Life Institute); a Magic: The Gathering reinforcement-learning project; and reasoning, evaluation, and red-teaming research contracts.
- **Mathematics** — graph theory, number theory, and theoretical computer science. Public results so far are graph-theory-centered: static coverage and persistence in tree-ball geometry ([preprint](/essays/branch-based-local-capture-in-tree-balls/)), and the annealed critical window for growing-radius domination in random regular graphs ([preprint](/essays/near-critical-growing-radius-domination.html)). - **Mathematics** — graph theory, number theory, and theoretical computer science. Public results so far are graph-theory-centered: static coverage and persistence in tree-ball geometry ([preprint](/essays/branch-based-local-capture-in-tree-balls/)), and the annealed critical window for growing-radius domination in random regular graphs ([preprint](/essays/near-critical-growing-radius-domination.html)).
- **Computer systems and high-performance computing** — the Weenix kernel, a TCP/IP networking stack from scratch in Go, and micro-architectural performance work (SIMD, hardware counters via PAPI, RAPL energy, cross-ISA ports across AVX2 / ARM NEON-SVE / RISC-V V) on Brown's OSCAR HPC cluster. - **Computer systems and high-performance computing** — the Weenix kernel, a TCP/IP networking stack from scratch in Go, and micro-architectural performance work (SIMD, hardware counters via PAPI, RAPL energy, cross-ISA ports across AVX2 / ARM NEON-SVE / RISC-V V) on Brown's OSCAR HPC cluster.
- **Machine learning** — order-invariant ICD-10-CM embeddings (under review at *JAMIA*, deployed calculator), the NeuroPose 3D-kinematics system in Liqi Shu's lab at Brown Neurology, and ongoing research engineering at [NeuroAI](https://neuroai.health). Undergraduate work has been clinically focused; graduate study broadens the scope. - **Machine learning** — order-invariant ICD-10-CM embeddings (under review at *JAMIA*, deployed calculator), the NeuroPose 3D-kinematics system in Liqi Shu's lab at Brown Neurology, and ongoing research engineering at [NeuroAI](https://neuroai.health). Undergraduate work was clinically focused; my current work broadens the scope.
Computer vision and security thread through all four but do not stand on their own. Computer vision and security thread through all four but do not stand on their own.

6
content/work.md
View File

@ -3,6 +3,7 @@ title: Work
work: true work: true
description: Research engineer working on technical AI assurance — verifiable inference, model evaluations, systems and cryptography. description: Research engineer working on technical AI assurance — verifiable inference, model evaluations, systems and cryptography.
history: history:
- date: "2026-09-03"
- date: "2026-08-29" - date: "2026-08-29"
- date: "2026-08-28" - date: "2026-08-28"
@ -19,9 +20,8 @@ not be trusted. That question spans cryptography, systems, evaluations, and
mathematics, which is roughly the shape of my background. mathematics, which is roughly the shape of my background.
I am a MARS V fellow with the [Cambridge AI Safety Hub](https://caish.org/mars), I am a MARS V fellow with the [Cambridge AI Safety Hub](https://caish.org/mars),
mentored by James Petrie (Future of Life Institute), and a graduate student in mentored by James Petrie (Future of Life Institute). I previously studied
computer science and engineering at DTU; previously computer science and computer science and mathematics at Brown.
mathematics at Brown.
**Open to full-time research and research-engineering positions worldwide.** **Open to full-time research and research-engineering positions worldwide.**
::: :::