Hey everyone! 👋 I’m an AI & full-stack engineer. I mostly work on workflow automation, LLM stuff, RAG, AI detection, and a bunch of image/voice AI projects. A lot of it is already running in real production, which has been pretty fun (and painful sometimes 😄). I’ve built pipelines and task orchestration systems using things like Dspy, OpenAI APIs, and custom agents. One project I’m especially proud of is a support automation setup that ties together Slack, Notion, and internal APIs with an LLM. It ended up cutting response times by around 50%, which honestly felt great to see. I’ve also been pretty deep into RAG pipelines lately. Mixing vector DBs with graph DBs, doing hybrid search, and writing custom retrieval logic. All that kind of work just to make sure answers stay accurate and context-aware once things hit production. On the AI content detection side, I worked on tools for a moderation platform. Stylometry, embedding similarity, some fine-tuned transformers — kind of a mixed approach. It worked surprisingly well at catching GPT-generated text. For image AI, I set up tagging and moderation pipelines using CLIP and YOLOv8 on AWS Lambda + S3. It handles thousands of images a day for an e-commerce platform. Nothing fancy on the surface, but very solid under the hood. And for voice AI, I built a voice cloning and transcription service with Whisper and Tacotron2. ASR, TTS, CRM integration — the whole thing. Personalized voice assistants are actually doable now, which is wild. Overall, I focus on building scalable, production-ready AI systems end-to-end. From model selection or fine-tuning all the way to backend integration and deployment. That’s kind of my thing. If anyone wants to collaborate, swap ideas, or just chat about AI, feel free to ping me anytime. Always happy to talk 🤝