AI Engineer | Entry Level | RAG, LLM Evaluation, Machine Learning

Entry-level software engineer focused on building reliable AI systems from retrieval and evaluation through API deployment and monitoring.

• Built a bilingual Arabic-English RAG system for Saudi labour law using hybrid retrieval, reranking, grounded answers, citation validation, and refusal handling.
• Developed supporting AI infrastructure: a tool-calling agent runtime, Arabic NLP pipeline, and LLM evaluation harness with deterministic graders, judge calibration, confidence intervals, and cost controls.
• Built a real-time fraud-detection platform with calibrated ML scoring, explanations, drift monitoring, a FastAPI service, and a live operations dashboard.
• Integrate LLM APIs with schema-validated outputs, fallback handling, observability, and usage controls.
• Work with Python, TypeScript, JavaScript, Node.js, REST APIs, Git, and Cloudflare Workers.
• Use reproducible benchmarks, automated tests, and documented engineering decisions to compare system quality, latency, reliability, and operating cost.
• Completed a software engineering internship at A20Z.
• Seeking entry-level AI engineering, RAG, applied machine learning, or backend engineering opportunities.