Full-Stack & AI Dev | TypeScript, Next.js, React, Node
- $50k+
- Earned
- 5x
- Hired
- 5.0
- Rating
- 136
- Followers
Full-Stack & AI Dev | TypeScript, Next.js, React, Node
Built a little Mac app called Flip, and it somehow went viral on Twitter.
The idea is pretty simple. What if every window on your Mac had a back side where you could keep notes? So I built exactly that.
Flip any window, jot something down, flip back. Your notes stay attached to that window.
No extra apps to switch between.
Built natively for macOS, completely local, and free.
Check it out: https://flip.pylondev.com
Here’s the original tweet:
https://x.com/skimmycat20/status/2096580098506084400
2
3
184
AI-Driven Full Stack & Architecture Solutions
Introducing Beacon AI Beta: Get Cited by AI. Get Found by Customers.
We are thrilled to announce the launch of Beacon, our AI Search Visibility Platform, now available in beta.
As AI search engines like ChatGPT, Perplexity, Claude, and Google AI become increasingly central to how people find information, visibility across these platforms is critical. Beacon gives you the intelligence you need to own search — both traditional and AI.
Beacon doesn't just show you data — it tells you what to do with it. Our AI-powered recommendations provide specific, actionable insights to improve your presence across traditional search and AI platforms.
Get started free at hellobeacon.ai (http://hellobeacon.ai). No credit card required.
3
28
404
AI/ML engineer who builds custom models, not wrappers.
I just launched cargo-vouch, an open-source Rust tool that proves a function can't panic. No tests to write, no annotations to add.
Point it at a .rs file, and it builds a Kani proof harness for every function, then checks every input in bounds. Each function comes back with one of four verdicts:
🔴 BUG, with the exact input that triggers the panic
🟡 UNGUARDED, safe except at type extremes like i32::MAX
🟢 VERIFIED, provably panic-free
⏳ INCONCLUSIVE, when it cannot decide
Why I built it: AI writes Rust that passes cargo test, then panics on an edge input nobody tried. For example, numbers.iter().sum() looks fine until something hands it [i32::MAX, 1].
I ran it on 11 functions GPT-4o wrote and graded. GPT-4o's own grading got 4 of them wrong: it passed three that overflowed and failed one that was fine. cargo-vouch called all four correctly, with the triggering input for each real panic.
The honest limit: it is built for loop-light code. Parsers and loop-heavy functions return INCONCLUSIVE, never a false pass. I would rather say that than oversell it.
If you write Rust, I would like your feedback.
Repo - https://lnkd.in/eHirVFQq
(https://lnkd.in/eHirVFQq)cargo install cargo-vouch
#rustlang (https://www.linkedin.com/search/results/all/?keywords=%23rustlang&origin=HASH_TAG_FROM_FEED) #opensource (https://www.linkedin.com/search/results/all/?keywords=%23opensource&origin=HASH_TAG_FROM_FEED) #formalverification (https://www.linkedin.com/search/results/all/?keywords=%23formalverification&origin=HASH_TAG_FROM_FEED)
0
48
Stigmergic consensus for multi-agent / multi-model systems. A learned, stateful alternative to majority vote and self-consistency: agents deposit weighted signals into a shared pool, a short truth-discovery loop converges on consensus, and cross-run pheromone memory teaches the swarm which agents to trust. Pure Python, zero dependencies, provider-agnostic.
0
44
PRAXIS is my MSc dissertation project at the University of Leicester: an end-to-end deep-learning system for voice-based biomarkers, designed and built from scratch.
I architected and implemented the full pipeline: a self-supervised speech representation model plus a downstream biomarker system, and contributed multiple novel technical and methodological advances, documented in a 15,000+ word dissertation with full research rigour.
What I did:
Designed a custom deep-learning architecture for speech/audio
(self supervised learning + domain adaptation)
Developed several original contributions in [voice-biomarker modelling/representation learning] (kept high-level to protect the method)
Built a reproducible, rigorously evaluated pipeline end-to-end: data → model → results
0
82
AI Chatbot Developer | Fullstack Engineer
Senior Full-Stack Dev | AI Products | Node/React/LLMs
Senior Full-Stack Dev | AI Products | Node/React/LLMs
Affordable AI - Maximizing Your Investments.
Affordable AI - Maximizing Your Investments.
View more →
Using data to drive business success.
Using data to drive business success.
View more →
Designing and building seamless web experiences.
Lexa — AI Legal Assistant Chatbot
Lexa is Pakistan's first AI-powered legal assistant, built to provide lawyers and law students with instant legal guidance 24/7. Its core chatbot uses AI to simplify complex legal queries, offering quick access to statutes, case laws, and over 2.5 lac judgments. Beyond chat, the platform supports legal drafting templates, MCQ practice for the GAT exam, and detailed judgment analysis — making legal research faster, more accurate, and accessible anytime, anywhere.
1
60
Thrill Pay — Buy Now, Pay Later App
Thrill Pay is a Buy Now, Pay Later application that integrates directly with your banking app. It checks your credit score to determine whether you're eligible for BNPL purchases, then lets you buy a range of gift cards on flexible payment terms. I led the UI/UX research and handled the front-end development for the project.
1
47