I help teams turn AI ideas into real, production-ready products, not just flashy demos that break in a week. I’ve built and shipped systems like: > Text → image / audio / video > Speech-to-text, voice transcription, and TTS > Voice agents & audio pipelines > End-to-end LLM-powered apps Tech-wise, I’m comfortable across the stack: > Backend: Python (FastAPI), Node.js, Scala, Elixir > Frontend: JavaScript / TypeScript, React, Next.js, a bit of Dart when needed > AI / ML: OpenAI, open-source LLMs, Whisper-style STT, TTS models, embeddings, vector DBs > Data: SQL (Postgres), synthetic data generation, data augmentation > Infra: Docker, cloud deployments (AWS/GCP), cost-aware scaling, production monitoring I’m used to jumping in early, helping shape prototypes, and then staying through hardening, optimization, and real user traffic. I care a lot about stability, performance, and cost, especially when models hit production. Clean systems > flashy demos. If that mindset matches what you’re building, happy to connect 🤝