Production-grade multimodal RAG for financial document intelligence. Chart understanding · hybrid retrieval · numeric guardrails · multi-tenancy · full observability.

🤖 An intelligent ATS (Applicant Tracking System) powered by Spring Boot 3, 智谱AI & Milvus. Features: AI resume parsing, RAG semantic search, async pipeline, recruitment funnel analytics. | 智能招聘管理系统：AI 简历解析、RAG 语义搜索、异步处理管道、招聘漏斗分析

AEM library that automatically invalidates cached CDN resources on content updates. Supports flexible configuration, background processing, and extensibility. Provides APIs and extension points for custom integrations. Reduces manual CDN cache invalidation effort. Out-of-the-box Akamai integration.

A self-hosted, high-performance workflow orchestrator for resilient microservices. Features event-sourced execution, atomic idempotency, per-tenant rate limiting, poison-pill DLQs, and a REST management API.

Estudo de caso técnico de uma plataforma web para auditoria patrimonial, análise jurídica, integração de dados e geração de relatórios.

AI-augmented backend system with async LLM processing, Redis caching, and scalable architecture for intelligent task management. Integrates Google Gemini, AWS S3, JWT auth, and is k6 load-tested for high-concurrency performance.

Scalable event processing for high-throughput systems

Production-style log analysis system built to reduce manual debugging time. Async processing, single consistent DB write per analysis, and safe fallbacks for incomplete or inconsistent AI responses.

☕ The high-performance REST API for LevelUp, a gamified learning platform. Built with Java 21 and Spring Boot 4, featuring asynchronous task verification, JWT security, and a complex XP/achievement engine powered by PostgreSQL.

Asynchronous document processing service with configurable pipeline, pluggable providers, and event-driven architecture using Redis Streams and background workers.

AI-powered travel itinerary generator using Cloudflare Workers, Firestore, and OpenAI's GPT-4. Features asynchronous processing, real-time status tracking, and comprehensive validation.

An observable, fault-tolerant AI pipeline for converting meeting audio into structured decisions and tasks.

AI-powered backend for user requests, enabling seamless chatbot integration... Created at https://coslynx.com

Distributed RAG ingestion pipeline with idempotent vector indexing, DLQ-backed retries, and deterministic failure recovery for production AI systems

Event-driven notification system for email, push, and async message delivery.

Production-grade backend demonstrating asynchronous job processing with BullMQ, Redis, PostgreSQL, and Express. Features background workers, retry mechanisms, dead-letter queues, rate limiting, structured logging, and resilient REST APIs.

mern redis kubernetes docker argocd gitops ci-cd distributed-systems async-processing

Symfony project with RabbitMQ using Hexagonal Architecture and Domain Events for scalable and event-driven applications

AI workflow orchestration system for document analysis. Async pipelines, LLM integration, response validation, retries, circuit breakers, and cost observability.

A containerized multi-service backend using Python FastAPI and Docker, implementing asynchronous processing and inter-service communication patterns.