Mohsin Hasan Khan

Mohsin Hasan Khan

Co-founder and Chief Scientist

NeuralHQ.ai

Mohsin is the Co-founder and Chief Scientist at NeuralHQ.ai, where he leads the development of AI agents for real-world applications. A Kaggle Grandmaster and former Analytics Vidhya rank #1, he brings deep expertise in machine learning and a passion for solving complex problems. With a strong track record in competitive data science, he enjoys exploring and discussing the latest in ML. His work combines practical AI innovation with a drive to push boundaries in agentic intelligence.

Learn how to train specialized AI agents using smaller models (8B-16B parameters) that can outperform GPT-4 on specific tasks. These agents can reason through problems, maintain context across multi-turn conversations, use tools, and execute complex workflows - all while being more cost-effective than large general models.

We'll be using our own custom LLM agent framework built from scratch, not relying on existing frameworks like Google's AgentSDK or similar tools. This gives you complete control over the agent architecture and training process.

What You'll Learn:

  • Training agents for multi-turn conversations and context retention
  • Creating data that teaches agents to reason and use tools
  • Building evaluation systems for agent performance
  • Fine-tuning smaller models to beat larger general-purpose ones
  • Making agents reliable for specific workflows and tasks
  • Working with our custom agent framework for maximum flexibility

Prerequisites:

  • Python programming experience
  • Basic understanding of machine learning

We'll demonstrate real examples where our 8B agents handle complex multi-turn conversations and reasoning tasks better than ChatGPT and Claude on specific domains.

Note: You'll get all training code, datasets, evaluation tools, and our custom agent framework used in the session.

Read More

Managing and scaling ML workloads have never been a bigger challenge in the past. Data scientists are looking for collaboration, building, training, and re-iterating thousands of AI experiments. On the flip side ML engineers are looking for distributed training, artifact management, and automated deployment for high performance

Read More

Managing and scaling ML workloads have never been a bigger challenge in the past. Data scientists are looking for collaboration, building, training, and re-iterating thousands of AI experiments. On the flip side ML engineers are looking for distributed training, artifact management, and automated deployment for high performance

Read More
Book tickets View all speakers

We use cookies essential for this site to function well. Please click to help us improve its usefulness with additional cookies. Learn about our use of cookies in our Privacy Policy & Cookies Policy.

Show details