I build end-to-end, intelligent applications—from responsive user interfaces to the robust, containerized infrastructure that powers them. My focus is on seamlessly integrating Generative AI into practical workflows and scaling those microservices reliably from development to production.
Currently engineering production-grade AI systems and applications with a focus on:
- GenAI & RAG: Architecting Retrieval-Augmented Generation applications and integrating LLMs into core software products.
- AI Workflows: Orchestrating complex, multi-step AI agent workflows and automation using LangGraph and n8n.
- Full-Stack Architecture: Developing robust backend microservices with FastAPI and Flask, paired with dynamic frontends using React.js.
- DevOps & Infrastructure: Containerizing and deploying applications at scale using Docker, Kubernetes (K8s), Helm, and Harbor, with CI/CD pipelines managed via Jenkins.
Frontend & Backend
React.js, Python, FastAPI, Flask, Microservices Architecture
AI & LLM Integration
GenAI, RAG Applications, LangGraph, n8n
DevOps & CI/CD
Jenkins, CI/CD Pipelines
Infrastructure & Orchestration
Docker, Kubernetes (K8s), Helm Charts, Harbor
- Shipping: End-to-end GenAI applications powered by scalable microservices.
- Learning: Advanced agentic workflows and optimizing highly available Kubernetes deployments.
- Open to: Collaborative projects involving full-stack AI integrations and resilient MLOps infrastructure.