Software EngineerBackend & Distributed SystemsFull-StackAgentic AI / LLM Engineering
Software Engineer focused on backend architecture, distributed systems, full-stack products, and production AI. Builds reliable services and agentic systems with TypeScript/Node.js, PostgreSQL, Redis, Docker, AWS, and modern LLM tooling. Hands-on with agent planning, tool calling, RAG, memory, multi-agent workflows, structured outputs, human-in-the-loop controls, evaluation, observability, retries, and long-running execution. Founder and lead engineer of Ryuksaidso, an agent reliability and control-plane platform. Uses AI coding and research tools to accelerate implementation, debugging, documentation, refactoring, and test generation, followed by human review, automated validation, security checks, and architecture verification before changes ship.
The stack behind my production backend, distributed systems and agentic AI engineering
Languages
TypeScript
JavaScript
SQL
Python
Backend
Node.js
Express.js
Fastify
NestJS
REST APIs
WebSockets
Microservices
Event-Driven Architecture
Frontend
React.js
Next.js
Redux
Tailwind CSS
Data
PostgreSQL
MongoDB
Redis
pgvector
Prisma
AI / Agents
AI Agents
Multi-Agent Systems
Planning
Tool Calling
Memory
RAG
Embeddings
Structured Outputs
HITL
LangChain
LangGraph
LLM Engineering
Local LLMs
Secure LLM Harnesses
Fine-Tuning
LoRA/QLoRA
Quantization
GGUF
Inference Optimization
Model Routing
Cloud / DevOps
AWS EC2
IAM
Docker
Docker Compose
NGINX
CI/CD
Linux
Prometheus
Grafana
Loki
Engineering
System Design
Distributed Systems
API Security
Authentication
RBAC
Rate Limiting
Caching
Observability
Performance
DSA
AI-Augmented Development
LLM-assisted coding
Debugging
Test generation
Documentation
Implementation acceleration
Verification
Human-in-the-loop review
Selected Projects
Production systems across agentic AI, real-time products and open-source tooling
Ryuksaidso
Production-oriented control plane for operating AI agents with planning, tracing, approvals, evaluations, versioning, knowledge retrieval, and multi-provider failover. Runs on a Next.js/React dashboard, stateless TypeScript/Node.js services, Redis + BullMQ workers, PostgreSQL + Prisma with pgvector, and Dockerized AWS EC2 infrastructure behind NGINX.
Built a gaming-focused social platform with real-time communication, authentication, scalable APIs, Redis-backed functionality, and Dockerized backend services.
Production-oriented agent reliability and control plane designed to operate AI agents with production software discipline. The platform centers on planning, tracing, approvals, evaluations, versioning, knowledge retrieval, and multi-provider failover.
Next.js/React dashboard for users, workspaces, agents, tools, providers, runs, approvals, traces, analytics, profiles, and administration.
API Layer
Stateless TypeScript/Node.js services with validation, authentication, RBAC, rate limiting, provider routing, health/readiness endpoints, and horizontal-scaling support.
Agent Runtime
Planning, task decomposition, tool calls, memory/state, structured outputs, retries, human approval, execution traces, and recovery.
Async Compute
Redis + BullMQ workers for long-running agent execution, browser automation, ingestion, scheduled jobs, retries, and workload isolation.
Data Layer
PostgreSQL + Prisma for transactional data, pgvector for semantic retrieval, and Redis for queues, caching, locks, and coordination.
LLM Layer
OmniRoute, Ollama, and OpenAI-compatible providers with local/cloud routing, quantized/fine-tuned model support, and controlled tool execution.
Production Infrastructure
Dockerized services on AWS EC2 behind NGINX with IAM, security groups/firewall controls, service isolation, health checks, and controlled network exposure.
Prometheus metrics, Grafana dashboards, Loki logs, audit trails, agent traces, worker visibility, and operational health monitoring.
Agent control plane
Experience & Education
The path from full-stack intern to founder & lead AI engineer
Experience
Founder & Lead Software / AI Engineer
2026 – Present
Ryuksaidso
Built and deployed Ryuksaidso, an agent reliability and control-plane platform for operating AI agents with production software discipline.
Designed the control plane around agent definitions, tools, providers, versions, runs, traces, approvals, policies, API keys, RBAC, tenant isolation, audit history, and operational visibility.
Developed and maintained a location-based full-stack platform with secure authentication, scalable APIs, and production-oriented application architecture.
Built frontend and backend functionality using React, TypeScript, Node.js, PostgreSQL, and REST APIs.
AI-assisted engineering: Use AI tools as force multipliers for implementation, investigation, refactoring, documentation, and tests while retaining responsibility for correctness, security, architecture, and final code review.
Leadership & Open Source
Founder, Ryuksaidso — agent reliability/control plane, agent orchestration, automation, secure local AI, and scalable backend systems.
Creator, BackendOS — open-source backend framework/toolkit for reusable production-oriented architecture.
Let's Build Something Great
Open to AI engineering, product, and full-stack collaboration opportunities.