Skip to content
View levineuwirth's full-sized avatar
💭
https://git.levineuwirth.org
💭
https://git.levineuwirth.org

Highlights

  • Pro

Block or report levineuwirth

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
levineuwirth/README.md

Levi Neuwirth

Work · CV · Website · Email · GPG · ORCID

I work on technical AI assurance, establishing verifiable claims about what a model actually did, when the operator, the evaluator, or the model itself may not be trusted. This spans cryptography, systems, evaluations, and mathematics, precisely the shape of my background. I'm a MARS V fellow with the Cambridge AI Safety Hub, mentored by James Petrie (FLI), and a graduate student in computer science and engineering at DTU; previously CS and mathematics at Brown.

I am open to full-time research and research-engineering positions worldwide.

Selected work

Verifiable LLM inference (MARS V, ongoing) — zero-knowledge proofs for cryptographic verification of claims about LLM training, inference, and deployment. My contributions are merged upstream into JamesPetrie/VerInf: a dry-run profiler with a manifest contract, cost model, execution DAG, and partition scorecard, plus cost-model corrections matching the paper's analysis (merged PRs). Currently porting the verifier from single-chip to multi-GPU and working on mathematical techniques for further optimization. Technical write-up expected Q4 2026, for review and publication.

Frontier-model evaluation and red-teaming — reasoning evaluation, red-teaming, RL environments, and evaluation research under contract. What I can discuss publicly is limited.

proof-broker — brokers proof goals from Lean 4 and Rocq through a shared IR to SMT solvers, ATPs, and LLM provers, then verifies returned certificates and lifts proof terms back to the home system. The verifier is strictly fail-closed: it refutes the negated goal, checking for smuggled axioms rather than trusting prover output.

icd_embeddings — order-invariant ICD-10-CM embeddings for 30-day readmission and post-discharge mortality, trained on the Nationwide Readmissions Database. Our manuscript is under review at JAMIA.

Also

Systems and performance: pmacs (Rust-cored, Lua-scripted editor), kyber-simd-profiling (SIMD post-quantum cryptography, cross-ISA), LeVCS (federated version control with signed authority chains), the Weenix kernel, and a TCP/IP stack written from scratch. Mathematics: two graph-theory preprints, on tree-ball geometry and growing-radius domination. Research engineering: neuropose, 3D kinematics in Liqi Shu's lab at Brown Neurology.

Primary Tools

Rust, Python, C/C++, OCaml, Haskell, Go. Cryptography, distributed systems and HPC, formal methods, ML evaluation.

I have worked with many other tools in the past to various extents, and the above list is certainly not exhaustive.


Most of my development is being moved to my Forgejo instance, mirrored here. Current is what I'm actually working on this month, while Vita is the most formal record.

Pinned Loading

  1. JamesPetrie/VerInf JamesPetrie/VerInf Public

    Python 2 4

  2. proof-broker proof-broker Public

    Brokers proof goals from Lean 4 and Rocq through a shared IR to SMT solvers, ATPs, and LLM provers, then verifies returned certificates and lifts proof terms back to the home system.

    OCaml

  3. pmacs pmacs Public

    Parallel Emacs — a Rust-cored, Lua-scripted editor in the Emacs tradition. Development, issues, and PRs happen here; self-hosted mirror at git.levineuwirth.org.

    Rust

  4. icd_embeddings icd_embeddings Public

    A permutation-invariant deep-learning model for 30-day unplanned readmission and 30-day post-discharge mortality, trained on ICD-10-CM diagnosis-code sets from the Nationwide Readmissions Database.…

    Python

  5. kyber-simd-profiling kyber-simd-profiling Public

    Profiling ML-KEM (Kyber): performance and energy implications of SIMD-optimized post-quantum cryptography.

    Go

  6. neuropose neuropose Public

    A 3D pose-estimation and kinematic-analysis system for neurological-recovery research, developed in Liqi Shu's cross-disciplinary laboratory at Brown University.

    Python 1