Available for select collaborations

Hi, I'm Tseka

AI-Native Builder

AI & System Builder

I design and build AI-powered products from zero to one. Focused on making complex technology feel simple, useful, and beautiful—shipping fast and iterating in public.

Trusted by collaborators across AI, design & engineering

See my work

AI & System Builder

I design and build AI-powered products from zero to one. Focused on making complex technology feel simple, useful, and beautiful—shipping fast and iterating in public.

See my work

Core Infrastructure & Platforms

Claude Code

Antigravity

OpenAI Codex

LangChain

n8n

PyTorch

Next.js

React 19

TypeScript

Tailwind v4

Python

PostgreSQL

Prisma

Vercel

Turborepo

Figma

Framer

Storybook

PostHog

Notion

Linear

Stripe

Claude Code

Antigravity

OpenAI Codex

LangChain

n8n

PyTorch

Next.js

React 19

TypeScript

Tailwind v4

Python

PostgreSQL

Prisma

Vercel

Turborepo

Figma

Framer

Storybook

PostHog

Notion

Linear

Stripe

github / TsekaLuk

Commits

public contributions

Repos

open source projects

Years

building in public

Languages

actively shipping in

Mission

My focus is on robust engineering, AI-native products, and scalable systems to deliver real-world impact.

AI Agents

UX Engineering

Full-stack Architecture

Systems Design

Open Source

Product Strategy

/ How I work

Path to shipped features

Architecture

Mapping out the system constraints, data flow, and UI surface. Deciding exactly what to build and what not to build.

Implementation

Deep focus engineering. Translating the mental model into solid Next.js and Python code with robust AI integrations.

Refinement

Polishing the sharp edges. Adding micro-animations, optimizing performance, and listening closely to telemetry and user feedback.

/ Selected Works

Shipped to production

View all 22 projects

any2md

Most converters silently drop formulas, tables, and cross-references. any2md uses a dual-engine—PyMuPDF for text + Qwen-VL for vision—then DeepSeek LLM reconstructs context via layered prompt + few-shot + CoT. Processes 68 pages/min with 85% table structuring and 90% LaTeX formula preservation. Imported 20,000+ pages into a team knowledge base in one week, cutting manual cleanup by 70%.

PythonVLMLLM

Low-Altitude Economy Research

Everyone assumed perceived risk would deter UAM adoption. Our TAM–SEM model on 2,609 respondents (93.1% recovery rate, KMO=0.951) proved the opposite: risk positively drives willingness to adopt (β=0.262, p<0.001). We also mined 1,695 Bilibili comments with SnowNLP to map public sentiment. The “risk paradox” finding challenged a decade of technology adoption literature. Provincial First Prize.

SEMNLPPython

Nebutra Sailor

Enterprise-grade monorepo powering 4 apps (marketing, dashboard, docs, studio) from 6 shared packages. Next.js 16 + React 19 + Tailwind v4, with a custom design token pipeline, 541 tree-shakable icons, and multi-theme engine supporting 6 oklch color schemes. Ships features 3x faster than separate repos.

Next.js 16TurborepoAI SaaS

Synergistic Equilibrium

MCM/ICM 2025 (Problem B): built a system dynamics + NSGA-III multi-objective optimizer balancing tourist flow, environmental quality, and social satisfaction. Achieved 8.3% tourist prediction error with R²>0.5 on a three-dimensional coupled model. Competed against 28,000+ teams globally. Honorable Mention.

NSGA-IIISystem DynamicsPCA-KMeans

/ Constellation