-000000?style=for-the-badge&logo=x&logoColor=white){kind=icon}
I'm Montassar Hajri, an AI Agent Software Engineer from Tunisia, specializing in building intelligent autonomous systems that can reason, plan, and execute complex tasks. I architect and develop multi-agent systems, RAG pipelines, and LLM-powered applications that solve real-world problems.
🔭 Currently: Developing autonomous AI agents for production environments
🧠 Focus Areas: Multi-agent orchestration, RAG systems, LLM fine-tuning, and agent evaluation frameworks
⚡ Passion: Creating AI systems that can learn, adapt, and collaborate with humans
🌍 Location: Tunisia | Open to remote opportunities worldwide
- Agent Architectures: ReAct, Plan-and-Execute, Reflection, Tree of Thoughts, Multi-agent Systems, Autonomous Agents
- LLM Integration: OpenAI, Anthropic, Google, Meta, Mistral, xAI, DeepSeek, Qwen, GLM, Kimi, ERNIE - Custom fine-tuning & RLHF
- RAG Systems: Advanced retrieval, vector databases, hybrid search, semantic caching, GraphRAG, Contextual retrieval, re-ranking
- Agent Frameworks: LangChain, LangGraph, LlamaIndex, CrewAI, AutoGen, Semantic Kernel, Swarm, PydanticAI
- Tool Integration: Function calling, MCP (Model Context Protocol), API orchestration, browser automation, code execution
- Evaluation: Agent benchmarking, LLM evaluation, A/B testing, human-in-the-loop systems, real-time observability
(Add your actual projects here - examples below)
Autonomous research agent system using GPT-4o with LangGraph for complex research tasks, document analysis, and report generation.
Production-grade RAG system with hybrid search, re-ranking, and query optimization for enterprise knowledge retrieval.
Multi-agent orchestration system enabling specialized agents to collaborate on complex problem-solving tasks.
