I design and deploy scalable LLM architectures, autonomous multi-agent workflows, and resilient backend systems. Hype-free engineering for real-world impact.
I am a GenAI Engineer with a background in Computer Science and Software Engineering, currently focused on designing and deploying scalable AI systems powered by LLMs, RAG architectures, agent orchestration frameworks, and MCPs.
Bridging the gap between traditional robust software architecture and next-generation artificial intelligence paradigms. No hype, just production-grade engineering.
The impact showcase. Focus on structural problem-solving and scalable system design over mere syntax.
Students often lack fast, objective feedback on ENEM essays; manual grading is slow and inconsistent.
React frontend for image upload, FastAPI backend for preprocessing (OpenCV) and Tesseract OCR; LangChain + Gemini evaluates text against ENEM criteria and stores results in PostgreSQL.
Automated, rubric-based scoring and actionable feedback reduce turnaround time and provide consistent evaluations at scale.
Small businesses need fast, 24/7 customer support on WhatsApp; manual responses scale poorly and lack personalization.
WAHA webhook → FastAPI processes messages → LangChain + RAG retrieves docs from ChromaDB → LLM composes replies; deployed in Docker for scalability.
Delivers instant, context-aware answers, increases booking rates and reduces support time by automating routine conversations.
The surgical stack. Organized by core niches to demonstrate systemic vision and architectural maturity.