The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
Bringing Genomic Analysis to the Edge 🚀
Developing solutions that directly impact human health requires speed, data privacy, and the right technology stack. Here is a quick look at our progress in applying Edge AI to complex genomic workflows—including biomarker analysis for variants like BRCA1 and BRCA2.
By leveraging powerful local processing tools like the Intel ecosystem alongside Visual Studio Code, we can build systems that process clinical insights efficiently, securely, and completely on-premise.
The future of diagnostic medicine relies heavily on bringing intelligence directly to the source of data.
Learn more at: EdgeVisionMed.com 🌐
#EdgeAI #MedTech #Genomics #Intel
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
Hey fellas 👐! I have just wrapped up the "Authentication Feature" design prototype for my new app.
🔐 Vaultra — AI-Powered Personal Finance App
Vaultra is a smart finance app that gives you real clarity over your money — not just your balance.
• 🌍 Aggregates all your accounts and wallets into one real-time, currency-converted total
• 🛡️ Shows a "safe-to-spend" balance after hiding committed bill money
• 🤖 AI that tracks spending patterns and intervenes before you overspend
Built for people who want their finances to feel simple, not stressful.
🚀 Follow me on LinkedIn for more updates [@Driss-Loulidi]
100% clean execution. It looks amazing
I recently built Job Board Hub, a MERN stack application that helps users discover remote job opportunities across different areas like technology, design, marketing, and more.
The idea is simple: job descriptions are often too long, repetitive, or hard to scan quickly. So I integrated an AI-powered job summary feature that allows users to generate a quick summary of each position and understand faster whether the role fits their profile.
But beyond the UI, this project was focused on demonstrating important backend decisions that are often overlooked.
The AI integration was built through an AI Gateway, making the system flexible enough to change models over time or even combine different providers in the future. I also implemented rate limiting to prevent abuse, protect token usage, and control costs.
Another key detail is the use of streaming responses, which improves the user experience by showing the AI summary progressively instead of waiting for the entire response to finish.
Some backend highlights:
- MERN stack application
- AI Gateway architecture
- AI-powered job summaries
- Streaming responses for better UX
- Rate limiting to protect API usage
- Clean backend structure for scalability
- Remote jobs organized by category:
This project helped me explore how AI can be integrated into real product experiences while keeping backend performance, scalability, and cost control in mind.
Job Board Hub is not just a job listing app — it’s a small example of how AI can make everyday platforms faster, clearer, and more useful.
Fluffless: Deterministic AI Proposal Engine
Project Overview / TL;DR
A high-performance Next.js web application that forces LLMs to write hyper-direct, senior-level technical pitches by anchoring generation to a persistent, client-side profile vault.
The Problem:
The freelance market is flooded with generic, AI-generated proposals that read like bloated cover letters. Clients ignore them because they lack technical depth and focus on "marketing fluff" rather than execution. Additionally, existing tools create massive UX friction by forcing users to manually re-type their past work experience for every single pitch.
The Solution:
I architected and deployed Fluffless to solve both the output quality and the user friction. I bypassed standard AI wrappers to build a constraints-based engine that only generates technically sound, highly specific proposals.
Key Technical Execution:
Client-Side "Profile Vault": To eliminate repetitive data entry, I engineered a persistent LocalStorage architecture. Users input their raw technical resume once, and the application silently passes this base context to the AI for all future generations, reducing user input to just the target job description.
Heavyweight AI & Prompt Engineering: I integrated the Groq API utilizing the massive Llama-3.3-70B reasoning model. I engineered a strict, one-shot prompt architecture loaded with negative constraints to completely strip out default "AI-speak" (e.g., words like leverage, delve, seamless) and force a rigid 4-step psychological sales structure (Hook -> Proof -> Execution -> Technical CTA).
Native Streaming Architecture: When the standard Vercel AI SDK introduced silent failures due to protocol mismatches, I bypassed the abstraction entirely. I built a custom, native JavaScript fetch and TextDecoder implementation to guarantee 100% stable, low-latency text streaming directly to the UI.
My Role:
Lead Full-Stack Developer & Prompt Engineer
Tools & Technologies:
Next.js (App Router)
React
Tailwind CSS
Groq API (Llama-3.3-70B)
Vercel
Project Links:
Live Site: https://fluffless.vercel.app/
Nice work🔥👏
Trending
Claude
Claude has entered the design space. How are you using Claude Design?
Contra University
Learn from expert creatives how to earn more using next-gen AI tools.
creativeaiflow
Creative AI workflows are evolving. What tools do you use, and what are their strengths and weaknesses?
portfolioreview
The best portfolios tell a story, not just show a grid. Share yours for feedback.
freelancerlife
Freelancer life is wins, pivots, and everything in between. What’s yours right now?