levineuwirth.org/content/about.md at 78d4adbfc4d5d30b2845dbc3ebc3a29cd72e0e55

title	tags
Levi Neuwirth — Vita	meta

For a less formal, more detailed introduction to who I am, see Me.

Documents

These are probably what you're looking for. A summary of the key points follows below!

Technical University of Denmark (DTU) — MSc in Computer Science and Engineering. September 2026 – expected 2028. Expecting PhD studies after.
Brown University — Sc.B. in Computer Science and Mathematics. August 2022 – May 2026
DIS Copenhagen / Københavns Universitet — Semester abroad. Fall 2024

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 (mentored by James Petrie, Future of Life Institute); a Magic: The Gathering reinforcement-learning project on OSCAR; agentic-systems work at xAI on grok-code-fast-1; and reasoning, evaluation, and red-teaming contracts with Anthropic, Mistral, and OpenAI.
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); more is in progress.
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. Undergraduate work has been clinically focused; graduate study broadens the scope.

Computer vision and security thread through all four but do not stand on their own.

Neuwirth L. Branch-Tube Persistence and Static Coverage in Tree-Ball Geometry. Preprint, July 2026. Preprint
Neuwirth L. Where Does SIMD Help Post-Quantum Cryptography? A Micro-Architectural Study of ML-KEM on x86 AVX2. Technical report, Brown University Department of Computer Science, April 2026. Report · Artifact
Shu L, Neuwirth L†, Wang X†, Zheng H†. Beyond Comorbidity Indices: An Order-Invariant ICD-10-CM Embedding for Readmission and Mortality Prediction. Under review at the Journal of the American Medical Informatics Association (JAMIA), 2026. Preprint · Calculator · Code

Zero-knowledge proofs for LLM verification. MARS V fellowship, Cambridge AI Safety Hub, July–October 2026; cryptographic verification of claims about model training, inference, and deployment. Public write-up expected October 2026.
NeuroPose clinical-implications manuscript. In preparation; target submission 2026–2027.
SIMD / PQC Phase 2 & Phase 3. Hardware performance counters (PAPI), RAPL energy, and cross-ISA ports (ARM NEON/SVE, RISC-V V).
Semantic-embeddings citation project. Early-stage work with NeuroAI, preprint expected summer 2026.
Magic: The Gathering reinforcement learning project. Early-stage work through Brown's HPC, expected late 2026.

Early Detection of Neurological Disorders through Video-Captured Kinematic Analysis. Ma J, Arms S, Kaneira L, Lall M, Chen K, Cabral W, Man D, Neuwirth L, Shu L. Poster, Brown / Rhode Island Hospital Neurology Summer UTRA Symposium, August 2025.
**"Order-Invariant ICD-10-CM Embedding for Readmission and Mortality Prediction: Toward Multimodal Generative Patient Models"**Shu L, Neuwirth L†, Wang X†, Zheng H†. IEEE/ACM Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE), August 2026, accepted.
Neuwirth L, Dasher AS. "Proving What a Datacenter Did: Verified Inference Between Adversaries." Talk, MARS V, Cambridge AI Safety Hub, July 2026. Accepted.

†Equal-contribution undergraduate authors.

Cambridge AI Safety Hub — MARS V Fellow. July – October 2026, Cambridge, UK. Selected for MARS V, a competitive part-time AI-safety research fellowship; working under James Petrie (Future of Life Institute) on zero-knowledge proofs for cryptographic verification of large language models.
Shu Laboratory, Brown Department of Neurology — Undergraduate Researcher and Technical Lead. October 2023 – Present. Technical lead on NeuroPose; co-lead developer on the ICD-10-CM embedding model.
NeuroAI Present. neuroai.health. Early-stage venture of academics and clinicians integrating deep learning, reinforcement learning, and generative AI into clinical and research workflows; leading research-engineering across model development, deployment infrastructure, and system design.
xAI Summer 2025, remote. Contributed to the training of grok-code-fast-1, xAI's agentic coding model; built LLM integrations into autonomous agent frameworks and resolved 50+ agentic tool-execution failures.
Independent Research Contracting — Anthropic, Mistral, OpenAI. 2025 – Present. Expert reasoning contributions in code and mathematics for agentic workflows, agentic task design and evaluation, AI safety, and red-teaming.

Weenix — Unix-like kernel in ~7,000 lines of C: virtual memory, VFS, system calls, threading, device drivers, interrupt handlers, and file systems. Custom linker support for running userspace x86-64 ELF binaries; extended with pipes and userspace preemption.
Networking Stack from Scratch — TCP/IP, RIP, UDP, and DNS in Go, supporting file transmission of up to 1 GB across 8-node networks. Extended with a fully RFC-compliant SSH implementation (2,000+ additional lines) supporting sustained sessions of arbitrary length.
SIMD / PQC Performance Study — Hand-written AVX2 assembly for ML-KEM / Kyber. 35×–56× speedup over compiler-optimized C for core NTT arithmetic; 5.4×–7.1× end-to-end KEM speedup, with a full statistical-analysis pipeline on Brown's OSCAR cluster.

For the complete index — additional artifacts, deployed ML, and smaller tools — see /cv/projects/.