AI Engineer specializing in multi-agent systems and memory-augmented architectures, enabling continuous learning and intelligent coordination. Focused on advancing adaptive AI solutions that integrate reasoning, retrieva…
AI Engineer specializing in multi-agent systems and memory-augmented architectures, enabling continuous learning and intelligent coordination. Focused on advancing adaptive AI solutions that integrate reasoning, retrieval, and scalability for enterprise innovation.
Built an end-to-end AI recruitment agent using FastAPI, LLMs, and ChromaDB, enabling semantic skill matching, automated candidate ranking, and agentic workflow orchestration, reducing manual screening time by 70% across 2000+ users and 100+ active job listings.
Designed an agentic JD analysis and candidate alignment system leveraging multi-step LLM reasoning, NLP embeddings, vector similarity search, and Python-based ETL pipelines, standardizing 2000+ candidate profiles with fuzzy matching and ML ranking algorithms to deliver scalable automated shortlisting and context-aware hiring insights.
- Built an end-to-end AI recruitment agent using FastAPI, LLMs, and ChromaDB, enabling semantic skill matching, automated candidate ranking, and agentic workflow orchestration, reducing manual screening time by 70% across 2000+ users and 100+ active job listings.
- Designed an agentic JD analysis and candidate alignment system leveraging multi-step LLM reasoning, NLP embeddings, vector similarity search, and Python-based ETL pipelines, standardizing 2000+ candidate profiles with fuzzy matching and ML ranking algorithms to deliver scalable automated shortlisting and context-aware hiring insights.
Fine-tuned and evaluated large language models GPT-2, GPT-3, and Qwen-2.5-14B for math and science reasoning, co-developing Ruh-R1-14B, a reasoning model, using supervised fine-tuning, chain-of-thought prompting, and Budget Forcing to simulate exam-like constraints under limited compute.
Improved reasoning consistency, interpretability, and deployment readiness through prompt engineering, token-budget optimization, and benchmark-based evaluation, delivering concise, logically coherent outputs for real-world educational AI systems.
- Fine-tuned and evaluated large language models GPT-2, GPT-3, and Qwen-2.5-14B for math and science reasoning, co-developing Ruh-R1-14B, a reasoning model, using supervised fine-tuning, chain-of-thought prompting, and Budget Forcing to simulate exam-like constraints under limited compute.
- Improved reasoning consistency, interpretability, and deployment readiness through prompt engineering, token-budget optimization, and benchmark-based evaluation, delivering concise, logically coherent outputs for real-world educational AI systems.
The AI-first Recruitment Operating System that unifies and automates the entire hiring lifecycle for modern enterprises worldwide.
Dr Job FZ LLC. 2026 © All Rights Reserved
