💻 AI Engineer & Full-Stack Developer building scalable, real-world systems

💡 I enjoy building AI systems where models, infrastructure, and user experience work together seamlessly. From RAG pipelines and multi-agent orchestration to scalable backend architectures and production-ready interfaces, I like transforming complex ideas into fast, reliable, real-world products.

• LLM-powered applications using RAG, OpenAI APIs, LangChain, LangGraph
• AI agent systems with orchestration, tool-calling, and workflow automation
• Scalable backend platforms using FastAPI, Node.js, PostgreSQL, Redis
• Intelligent systems combining AI + full-stack + infrastructure
• Distributed and event-driven systems with observability and async processing

• Build quickly, validate early, improve continuously
• Treat AI as a systems problem, not just a model problem
• Focus on reliability, latency, scalability, and user experience
• Prefer modular architectures and production-style engineering practices
• Learn by shipping real products and experimenting aggressively

• Making LLM systems more reliable with evals and hallucination control
• Exploring multi-agent workflows and AI orchestration systems
• Learning how modern AI infrastructure is deployed and scaled
• Building cloud-native and distributed backend systems
• Experimenting with efficient LLM fine-tuning and inference optimization

LLM-powered repository intelligence platform that analyzes GitHub repositories using RAG pipelines, vector retrieval, and optimized token workflows to improve developer understanding and navigation.

Tech: FastAPI · OpenAI · RAG · Vector Search · GitHub API

Multi-agent AI shopping assistant with contextual recommendations, orchestration workflows, and conversational product reasoning pipelines.

Tech: LangChain · FastAPI · AI Agents · REST APIs

Reproduced LoRA (Low-Rank Adaptation) for parameter-efficient LLM fine-tuning using PyTorch and HuggingFace, benchmarking memory efficiency vs performance tradeoffs.

Tech: PyTorch · Transformers · PEFT · NLP

Distributed systems simulation platform for analyzing transaction failures, retries, latency spikes, and traffic surges in payment workflows.

Tech: Go · Kafka · Redis · Docker · Observability

Cloud cost optimization and anomaly detection platform built around cloud-native analytics and infrastructure monitoring workflows.

Tech: AWS/GCP · PostgreSQL · Docker · Data Analytics

• AI/ML Engineering Internships
• Backend & Platform Engineering Roles
• Full-stack AI product development
• Cloud and Data Engineering
• Open-source and research collaborations
• Building ambitious AI systems with strong engineering depth

⭐ Building AI systems that are useful, scalable, and engineered for the real world.