AI Engineer | 3+ years Experience | RAG Systems, AI, LangGraph, Agentic AI

Summary

AI Engineer with 3+ years of experience building production-scale GenAI systems that turn complex enterprise data into plain-English answers. I focus on prompt architecture, agent orchestration, RAG, and reliable microservice backends that hold up under high-throughput live traffic. I don't ship bloated code or brittle wrappers.

Core skills

• Agentic AI & LLM Systems: LangGraph, LangChain, Multi-Agent Orchestration, Tool-Calling Loops, Agentic RAG, System Prompting
• NLP & Vector Search: Intent Routing, Context Window Optimization, ChromaDB, Fine-Tuning, Real-Time Speech/Text Processing
• Backend & Infrastructure: FastAPI, Python, PyTorch, Docker, MySQL, SQLite, Concurrent Inference

Experience & achievements

• Built rock-solid microservice backends (FastAPI, PyTorch) that process high-throughput live traffic without missing a beat.
• Structured multi-agent systems (LangGraph, LangChain) that reason, route intent, execute tool calls, and control state, not just output text.
• Kept models grounded in real enterprise data through hybrid retrieval, vector stores, and dynamic system prompts.
• Reduced query processing time by ~40% (from ~7 minutes to ~4.2 minutes) across 30 concurrent devices by implementing ThreadPoolExecutor-based parallel execution.
• Achieved 90–95% correct intent-routing accuracy across four specialized agents (classification, general query, tutorial, and custom reporting) in a production multi-agent system.
• Engineered a multi-class classification pipeline across 155K+ URLs, achieving 98.92% test accuracy and 0.97 macro F1 with Random Forest, benchmarked against SVM, XGBoost, LSTM, and fine-tuned BERT.

What I am looking for

I'm seeking AI Engineer roles focused on production-scale GenAI systems, agentic AI, and RAG for enterprise data problems, open to remote work and relocation to Saudi Arabia/GCC with employer sponsorship.