Adam

Would you hire me based on this resume: Applied AI Engineer / AI Systems Builder United States • GitHub: github.com/adamarchuleta • App: Omnia Scire (iOS & Web) SUMMARY Founder and applied AI engineer building production AI systems with persistent memory, real-time voice interaction, and scalable LLM infrastructure. Experienced in designing retrieval-augmented generation (RAG) pipelines, deploying AI services, and shipping multi-platform products across iOS and web. Focused on practical AI systems that automate workflows and integrate cleanly into real-world products. CORE SKILLS • AI & LLM Systems: LLM APIs (OpenAI, Anthropic, Gemini), Retrieval-Augmented Generation (RAG), embeddings & vector search, agentic workflows, tool calling, system prompt design • Backend & Data: Python, FastAPI, Supabase (Postgres, RLS, storage), SQL, API architecture, OAuth, Apple Sign-In, JWT • Client & UX: SwiftUI (iOS), Web (HTML, JavaScript, CSS), real-time voice (STT/TTS), WebSockets • Product & Infra: Stripe billing & subscriptions, App Store Connect, TestFlight, production deployment and monitoring EXPERIENCE Founder / Applied AI Engineer — Omnia Scire (2024 – Present) • Designed and built a production AI assistant platform across iOS and web • Implemented persistent long-term memory systems enabling cross■conversation context retention • Built retrieval-augmented generation (RAG) pipelines using embeddings and vector search• Designed modular AI architecture separating memory storage, orchestration, and inference layers • Developed real-time voice interaction using streaming STT/TTS and WebSockets • Deployed backend services using Python, FastAPI, and Supabase with secure authentication and RLS policies • Integrated Apple Sign-In, Stripe subscriptions, and usage-tracking infrastructure • Built and shipped a native iOS application using SwiftUI and distributed via App Store Connect and TestFlight PROJECTS • Venting with Omnia (Voice-First AI Application) – Built a voice-first AI companion application focused on real■time emotional support; implemented low■latency streaming voice input and response generation. • Omnia Translate – Developed a real-time multilingual voice translation system capable of detecting and translating speech across multiple languages . • Aurea – Built a quote and reflection application delivering curated philosophical insights and enabling journaling and sharing features. TECH STACK WebSockets • Stripe • Apple Sign■In Python • FastAPI • Supabase (Postgres) • OpenAI APIs • Vector embeddings • SwiftUI • EDUCATION Independent study in AI systems, distributed systems, and LLM engineering

Hire me because I don’t wanna do any marketing or branding. Here’s what I’ve built: linktr.ee/Get.Omnia.Apps

@zerohedge Good

*OPENAI EXECUTIVE KEVIN WEIL LEAVING COMPANY: WIRED

If you could have ChatGPT and Codex work together to make something, like ChatGPT does the planning and ideations and codex doing the coding, they probably would not come up with a great software. You would think they would, but no.

Can Codex and ChatGPT work on my idea without me doing anything?

@Cristiano It’s Gucci

What do you think? 😎

Wtf do you mean “JUST IN”

Crazy this is where England sent their prisoners

Supreme Leader ├── Research Lead │ ├── Research Agent │ └── Critic Agent ├── Build Lead │ ├── Builder Agent │ └── Critic Agent └── Strategy Lead ├── Research Agent └── Builder Agent

@Joey_Walker82 You’ve done the easy part

I have done it! I have finally submitted my app to the app store. It's been a long and tiring process as this is a completely new endeavour for me. I have learnt so much these last few weeks and I can't wait to get going with the marketing. Once it actually gets accepted that is. LFG!!

@OpenAI Can it edit videos ?

With computer use on macOS, Codex can now use any app by seeing, clicking, and typing with its own cursor. It runs in the background without taking over your computer, working on tasks like frontend iteration, app testing, or any workflow that doesn't expose an API.

Codex for (almost) everything. It can now use apps on your Mac, connect to more of your tools, create images, learn from previous actions, remember how you like to work, and take on ongoing and repeatable tasks.

For GPT 6

AI chips are quietly changing how we think about computers. For the longest time, the model was simple: • Hardware = fixed logic • Software = flexible logic But that line is starting to disappear. AI chips are built to run learning algorithms—systems that don’t just execute instructions, but adapt and evolve based on data. So now we have: • Hardware designed for flexible, evolving logic — What’s actually different? Traditional chips (CPU mindset): • General-purpose instructions • Step-by-step execution (if → then → else) • Deterministic and precise Think: apps, spreadsheets, operating systems — AI chips: • Massive parallel computation • Optimized for matrix math + vectors • Built for probabilistic systems Think: language, vision, pattern recognition — Here’s the real shift: 1. Hardware is no longer just executing—it’s running learned behavior You don’t program “recognize a cat” anymore. You train a model, and the chip runs what it learned. The logic isn’t in code branches… it’s in weights (numbers). — 2. “Software” starts to look like data Model weights (millions or billions of numbers) define behavior. They are: • generated through training • stored like data • executed like instructions So what are they—software or data? Both. — 3. Hardware and software are being designed together Companies like NVIDIA, Google, and Apple don’t just build chips. They design models → then design chips specifically to run those models. Hardware is now shaped by software needs. — 4. Computing becomes statistical Old world: • exact answers • deterministic logic AI world: • probabilities • approximations • “good enough” answers—fast This is a completely different philosophy of computing. — The bigger picture: We’re moving toward hardware that behaves less like a calculator… and more like a brain. Neural networks approximate brain structures. AI chips optimize how those structures run. — Where this is going: • Software-defined hardware Same chip, different model → completely different intelligence • Personal AI hardware Your device runs your model locally Your AI becomes tied to your hardware • AI-native systems Instead of: OS → Apps → Features We get: AI core → everything else Where the “app” is just an expression of intelligence, and hardware is just the vessel. — We’re not just upgrading computers. We’re redefining what computation even is.

At a deep level, hardware is just frozen software logic (transistors arranged to follow rules) And software is just dynamic logic that can change

@adam_archuleta" target="_blank" rel="nofollow noopener">producthunt.com/@adam_archuleta

American Society peeked in 2016

GPT 5.1 is way better than 4o

Why tf were they taxing social security😭🤦‍♂️