Quan D.

AI Engineer | Backend & Distributed Systems | Python Expert I build production-ready AI products and scalable backend systems -- from LLM applications and Computer Vision pipelines to distributed services, cloud infrastructure, and full-stack applications. My focus is not just on training models or building prototypes. I design and deliver complete systems that are reliable, observable, scalable, and ready for real-world traffic. Core Expertise 1. LLM & Agentic AI Systems * RAG applications and AI assistants * Multi-agent and agentic workflows with LangGraph, CrewAI, and LlamaIndex * LLM API integration and structured output pipelines * Prompt management, evaluation, tracing, and observability * Model serving with vLLM and scalable inference architectures * Async and queue-based AI generation pipelines * Langfuse-based tracing and prompt management 2. Computer Vision * Object Detection: YOLO * Multi-Object Tracking: ByteTrack, DeepSORT * Person Re-Identification: OSNet and embedding-based retrieval * Image classification and feature extraction * Real-time video processing pipelines * Edge/Server hybrid inference architectures * OpenCV and PyTorch 3. Backend Engineering & System Design * Python, TypeScript, Golang * FastAPI and NestJS * REST APIs and asynchronous backend services * Asyncio, multithreading, multiprocessing, and concurrent systems * Event-driven and queue-based architectures * Microservices architecture * Background workers and distributed job processing * Rate limiting, caching, retries, idempotency, and fault-tolerant workflows * API integrations including Stripe, Shopify, and third-party platforms 4. Distributed Systems & High Availability * Kafka-based event streaming systems * Redis caching, distributed coordination, and queues * Ray Serve for distributed inference * Horizontal scaling and stateless service design * Load balancing, health checks, automatic recovery, and high-availability architecture * PostgreSQL and Redis replication strategies * Cloud-native deployment architecture * Production system monitoring and incident debugging 5. Data Engineering * Apache Kafka * Apache Airflow and Dagster * ETL / ELT pipelines * ClickHouse and Google BigQuery * PostgreSQL, MySQL, MongoDB * Redis * Large-scale web crawling with Scrapy, Playwright, and Selenium 6. Cloud, DevOps & Observability * AWS, GCP, Oracle Cloud * Docker and Kubernetes * CI/CD pipelines * Linux server administration * Prometheus and Grafana * ELK Stack * New Relic * Splunk * Langfuse * Production logging, metrics, tracing, and alerting 7. Full-Stack Development * React.js and Next.js * TypeScript * React Native * Shopify application integrations What I Can Build I can help you design and build: * AI SaaS products * LLM-powered applications and AI agents * RAG systems * Computer Vision systems * High-throughput Python APIs * Distributed processing pipelines * Real-time event-driven systems * AI image/video processing platforms * Scalable backend architectures * High-availability cloud infrastructure * Data pipelines and analytics platforms * Full-stack MVPs and production applications I am comfortable working across the entire engineering lifecycle -- architecture, implementation, deployment, monitoring, performance optimization, and production debugging. If you have a complex AI or backend problem that needs more than a quick prototype, let's build it properly