Selected Work & Open-Source Architecture
MLX-QUANT & pureQTern
Ternary {-1, 0, +1} quantization engine and custom Metal GPU compute kernels achieving 12.80× memory reduction over FP16, paired with bit-exact C and Rust codecs.
Osaurus (osaurus-ai/osaurus)
Core Architect on the native Swift macOS harness for autonomous AI agents — persistent memory, local model execution, and cryptographic identity.
Headroom (PR #1418 — kompress Router)
Engineered per-content-type bias multipliers for kompress domain routing in Headroom, optimizing multi-domain context compression.
AgentField & Automated Verification
Multi-reasoner swarm orchestration with dynamic call graphs, async execution gates, and cryptographic Verifiable Credentials (VCs) per reasoning step.
Osiris (simplifaisoul/osiris)
Core Architect on Osiris — open-source real-time global intelligence and multi-source telemetry synthesis platform.
HF-Mac
Native Swift 6 macOS companion for local and remote model discovery, quantization inspection, and zero-overhead local inference.
Direct Portal, LinkedIn Contacts & 1-Click Outreach
David Ha
Co-founder leading evolutionary model merging, AI Scientist & collective intelligence in Tokyo.
Llion Jones
Co-founder & CTO overseeing novel foundation architectures and inference systems.
Ren Ito (伊藤錬)
Co-founder leading operations, strategic partnerships, and Tokyo talent expansion.
Hi! I built a live interactive Boids + 1.58-bit ternary inference portfolio specifically for Sakana AI's Systems & GPU Infrastructure team in Tokyo: https://sakana.vaked.dev (12.8x BitNet compression + Osaurus/Headroom OSS architect). Would love to connect! — Péter
Dear Sakana AI Founding & Engineering Team,
I built a dedicated interactive showcase and bilingual engineering dossier for Sakana AI's AI Systems & Multi-GPU Infrastructure Engineer role in Tokyo:
• Live Interactive Portfolio (Emergent Boids + Ternary Lattice): https://sakana.vaked.dev
• Tailored Resume / 職務経歴書 (PDF): https://sakana.vaked.dev/resume.pdf
• Systems Portfolio (PDF): https://sakana.vaked.dev/portfolio.pdf
• Full Application & Architecture Note: https://sakana.vaked.dev/application
My work centers on two pillars at the heart of Sakana AI's mission:
1. Low-Bit Foundation Model Compression (8b-is/MLX-QUANT & pureQTern): 12.80× memory reduction via BitNet b1.58 {-1, 0, +1} ternary quantization with custom Metal GPU kernels and zero-dependency C/Rust codecs.
2. Collective Multi-Agent Systems: Core Architect on Osaurus (osaurus-ai/osaurus — native Swift offline agent harness), contributor to Headroom (headroomlabs-ai/headroom PR #1418 — kompress domain-routing bias multipliers), and builder of AgentField multi-reasoner DAG orchestration.
Warm regards,
Péter József Lódri
https://www.linkedin.com/in/peter-lodri/
Technical Stack & Capabilities
Rust, C, Swift 6, Go — SIMD, custom Metal/WebGL2 GPU kernels, BitNet b1.58 {-1, 0, +1} ternary quantization (12.80× memory reduction), zero-dependency binaries.
Unity, Three.js, WebGL2, GLSL/HLSL shaders, oscilloscope vector synthesis, LiDAR/geospatial 3D telemetry (Osiris), procedural Web Audio.
Core Architect on Osaurus (osaurus-ai/osaurus) & Osiris (simplifaisoul/osiris), contributor to Headroom (PR #1418 kompress router), creator of AgentField verifiable DAGs.
9+ years shipping high-concurrency Go/Python/Rust/TS systems (ASAPP, DailyWire 110k concurrent users, institutional fintech ETL). Fluent English, native Hungarian, conversational multi-lingual + daily Japanese in Tokyo.
Why Sakana AI (サカナAI)
Sakana AI proves that nature-inspired collective intelligence — evolutionary model merging, The AI Scientist, and composable swarms of efficient specialists — beats brute-force monolithic scaling. My work in 1.58-bit ternary quantization (MLX-QUANT, pureQTern), context compression routing (Headroom PR #1418), and autonomous agent harnesses (Osaurus, AgentField) is built on the exact same conviction: when you compress foundation weights by 12.80× into {-1, 0, +1} and orchestrate them as verifiable swarms, a single workstation or compact GPU cluster becomes an evolutionary laboratory.
Sakana AIが推進する「自然界の群知能に学ぶ進化的モデル統合」と「自律型AIサイエンティスト」は、巨大単一モデルの力任せなスケーリングに対する最も美しい解答です。私が開発してきた1.58ビット三値量子化エンジン（MLX-QUANT / pureQTern、FP16比12.80倍圧縮）やマルチエージェント基盤（Osaurus / AgentField / Headroom PR #1418）は、まさに限られた計算資源から最大の創発的知能を引き出すためのシステム技術であり、東京のSakana AIチームでその推論・分散基盤を極限まで高速化したいと強く願っています。