
Building
Mythein Labs
An ultra-fast AI Superfactory for Physical R&D, focused on semiconductor manufacturing and superconducting material science.
- Multi-physics
- Design-search RL
- CUDA

I work on AI systems, RL infrastructure, CUDA kernels and multi-agent architectures. On this site you can find my work and my open-source projects on GitHub.
What I build day to day.

Building
An ultra-fast AI Superfactory for Physical R&D, focused on semiconductor manufacturing and superconducting material science.
Founding Engineer
AI for HVAC systems and energy products: error-code resolution, service-parts discovery and document understanding for field technicians.
Research notes, build logs and longer pieces.

A 12-line task for Sleep-Time Research (Sleep-Time Compute): two cycles, and a solver that beat our own accelerated baseline by 26x, after the system broke its own headline result twice and caught both breaks itself.

Super Turing, the engine I build at Mythein Labs: chromatic Gibbs sampling on an Ising lattice and replica-exchange annealing, fused into a CUDA kernel that is itself the RL environment step. From Maxwell's demon and p-bits to the kernel, the oracle that grades it, and the problem classes it fits.
A verifier-driven continual learning recipe that combines self-generated traces, replay, and a failure-driven curriculum to learn new task families while limiting forgetting.

A compact, agent-driven research harness for Mamba-2, Mamba-3, and Nemotron-H-style hybrid Mamba–Transformer MoE models on MLX and CUDA.
An open-source catalog of 19 agent-maintained skills spanning autonomous research, LLM post-training, GPU/TPU programming, and accelerated computing.
A memory layer for Recursive Language Models that records trajectories, extracts reusable strategies, and lifts a weaker model's benchmark score by 26% over three rounds.