Skip to content
View Hasan-Syed25's full-sized avatar

Block or report Hasan-Syed25

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please donโ€™t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this userโ€™s behavior. Learn more about reporting abuse.

Report abuse
Hasan-Syed25/README.md

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.

๐Ÿ“ Islamabad, Pakistan | ๐Ÿ“ง [email protected] | ๐Ÿ”— LinkedIn | ๐Ÿ’ป GitHub | ๐Ÿฆ Twitter

Twitter LinkedIn Gmail GitHub


๐Ÿš€ 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.


๐Ÿ’ผ Experience

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

๐Ÿ›  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

๐ŸŽ“ Education

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


๐ŸŒŸ 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 practicesโ€”connect with me to join the conversation!


๐Ÿ“Š GitHub Stats

GitHub Stats Top Languages

Popular repositories Loading

  1. MCP-Server-AlphaVantage MCP-Server-AlphaVantage Public

    Python 7 5

  2. HF2Reasoning HF2Reasoning Public

    Get any HF dataset to think/reason using HF2Reasoning.

    Python 2

  3. python-sdk python-sdk Public

    Forked from modelcontextprotocol/python-sdk

    The official Python SDK for Model Context Protocol servers and clients

    Python 1

  4. AI-Scientist-v2 AI-Scientist-v2 Public

    Forked from SakanaAI/AI-Scientist-v2

    The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search

    Python 1

  5. schedule_free schedule_free Public

    Forked from facebookresearch/schedule_free

    Schedule-Free Optimization in PyTorch

    Python

  6. spectrum spectrum Public

    Forked from QuixiAI/spectrum

    Python