Hasan-Syed25 - Overview

Syed Hasan

AI Engineer | RAG Specialist | Agentic Systems Architect

With 3+ years building enterprise-scale AI solutions, I specialize in retrieval-augmented generation (RAG), model optimization, and agentic architectures. Currently a Founding AI Engineer at 108-AI and a significant Hugging Face contributor (15+ models, 10k+ downloads), I'm passionate about advancing AI technologies that deliver measurable business impact.

πŸ“ Islamabad, Pakistan | πŸ“§ hasansyed8505@gmail.com | πŸ”— LinkedIn | πŸ’» GitHub | 🐦 Twitter

Twitter LinkedIn Gmail GitHub


πŸš€ Recent Projects

  • Dynamic Conversational AI Agent
    Engineered an Azure-based system that intelligently switches between API calls and RAG generation, reducing latency by 30% while maintaining 90% task completion accuracy.

  • Evidence-Based QA System
    Built a high-fidelity system with self-correction mechanisms for legal/financial domains, achieving 90% factual consistency in responses.

  • Scalable Agentic RAG Framework
    Designed a sophisticated hybrid retrieval strategy (BM25, dense vectors, RRF re-ranking) that improved search relevance by 30% compared to vector-only approaches.

  • GraphRAG-Inspired Document Processing
    Implemented context-preserving document chunking with regex-driven segmentation and graph-based linking for enhanced contextual understanding.

  • Llama-4 iRope Implementation
    Implemented iRoPE (Interleaved Rotary Position Embeddings) to enhance transformer models' long context handling capabilities.


πŸ’Ό Experience

  • Founding AI Engineer at 108-AI (Aug 2024 - Present)
  • Machine Learning Engineer at GenerexAI (Oct 2021 - Jul 2023)

πŸ›  Skills & Technologies

  • Core AI: Machine Learning, Deep Learning, NLP, Reinforcement Learning, LLMOps, Prompt Engineering, RLHF
  • Frameworks: PyTorch, TensorFlow, Hugging Face Transformers, LM Evaluation Harness
  • Languages & Libraries: Python, Pandas, NumPy, Weights & Biases
  • Cloud & DevOps: AWS, Microsoft Azure, GCP, Docker, MLOps
  • Specializations: Retrieval-Augmented Generation (RAG), Vector Databases, Agentic Systems

πŸŽ“ Education

National University of Science and Technology, Islamabad, Pakistan
B.E Software Engineering (GPA: 3.81)


🌟 About Me

I'm dedicated to creating AI systems that bridge the gap between cutting-edge research and practical business applications. I regularly share insights on AI advancements and best practicesβ€”connect with me to join the conversation!


πŸ“Š GitHub Stats

GitHub Stats Top Languages