Senior AI Platform Engineer & Technical Lead

Hi, I'm Niiaz

15+ years building scalable platforms that power AI products. Expert in multi-LLM orchestration, RAG systems, and cloud-native infrastructure. Transforming research into production-ready AI solutions.

View My WorkGet in Touch
Scroll down
About Me

From Research to Production-Ready AI

Full-Stack Engineer & Backend Systems Architect with 15+ years building scalable platforms. Currently leading technical development of AI-powered collaborative platforms with multi-LLM, multi-agent, and multi-modal capabilities.

AI & LLM Engineering

Multi-LLM orchestration with OpenAI, Anthropic, AWS Bedrock. Production deployment of Claude, Llama, Mistral models.

OpenAI APIClaude APIAWS BedrockLangChainLangGraph

RAG & Agent Systems

GraphRAG implementation, semantic routing, multi-agent collaboration with voting mechanisms.

GraphRAGPGVectorSemantic RoutingMulti-Agent

Backend Development

Python mastery with FastAPI, Django. Microservices, event-driven systems, real-time WebSocket communication.

PythonFastAPIDjangoCeleryPostgreSQL

DevOps & Infrastructure

Kubernetes orchestration on AWS/DigitalOcean. CI/CD with GitHub Actions, ArgoCD GitOps, comprehensive monitoring.

KubernetesDockerTerraformGrafanaPrometheus

Full-Stack Development

React 18+, TypeScript, Next.js for modern frontends. Real-time features, component architecture, state management.

ReactTypeScriptNext.jsTailwind CSSRedux

Data & Storage

PostgreSQL with PITR, Redis caching, vector databases, S3-compatible storage for scalable data solutions.

PostgreSQLRedisMongoDBElasticsearchS3
Portfolio

Featured Projects

Production AI systems I've architected and built, from multi-LLM platforms to enterprise infrastructure.

Sociail AI Platform

Next-generation AI-powered collaborative chat platform with multi-LLM, multi-modal, multi-agent capabilities. 5-layer distributed architecture supporting enterprise-grade features.

ReactFastAPIMatrix SynapseKubernetesAWS
30+ major featuresAuto-scaling infraReal-time streaming

Multi-LLM Orchestration

Intelligent routing system between OpenAI, Anthropic, AWS Bedrock models. Built voting and synthesis mechanisms for collaborative AI responses with 99.9% uptime.

OpenAIClaudeAWS BedrockLangChainRedis
Auto failoverLoad balancingTask-based routing

GraphRAG Implementation

Knowledge graph-based retrieval system with semantic routing and chunking. Achieved 3-5x performance improvement and 40% better accuracy over traditional RAG.

GraphRAGPGVectorPostgreSQLLangGraphFastAPI
Semantic chunking40% accuracy boostSub-second queries

Multi-Agent System

Collaborative multi-agent conversation system with voting mechanisms and response synthesis. Autonomous agent coordination for complex task completion.

LangChainLangGraphCeleryWebSocketReact
Voting mechanismsAgent collaborationReal-time UX

Production K8s Infrastructure

Enterprise Kubernetes infrastructure on AWS with auto-scaling, GitOps deployment, and comprehensive observability. Full CI/CD pipeline with GitHub Actions and ArgoCD.

KubernetesHelmArgoCDTerraformPrometheus
Auto-scaling HPAGitOps workflowFull observability

Real-time AI Streaming

Optimized streaming solution for AI responses with collapsible headers/footers. WebSocket-based real-time communication with Matrix protocol extensions.

WebSocketMatrix ProtocolRedisReactTypeScript
Stream optimizationCustom artifactsEnhanced UX
Contact

Let's Work Together

Have a project in mind or want to discuss AI solutions? I'd love to hear from you.

Get in Touch

I'm always open to discussing new projects, creative ideas, or opportunities to be part of your vision.

Location

Madrid, Spain

Open to Opportunities

Currently available for freelance projects, consulting, and full-time positions in AI/ML engineering.