Li Jin
A practitioner in the AI field who initially focused on biometric recognition and facial recognition, later transitioning to the integration of traditional microservices with multi-agent systems and RAG retrieval technologies. Actively engaged in practical work and knowledge sharing within the Frontier Deployment Engineer (FDE) domain.
Timeline (last 90 days)
Teacher Li Jin introduced in a livestream class that the FDE concept is becoming hot in 2026.
Teacher Li Jin suggested an advanced FDE technical path: first do AI agent development, then go deeper into model fine-tuning, distillation and pretraining.
Teacher Li Jin pointed out that many companies do not lack the conditions for fine-tuning but are unwilling to do it, the core reason being that the difference in effect before and after fine-tuning is hard to verify; sometimes the effect actually gets worse after fine-tuning, and hiring one person specifically to do fine-tuning can cost several hundred thousand a year.
Teacher Li Jin's research direction over the past two years has been to deeply combine traditional microservices with multi-agent systems and RAG retrieval, with end-to-end implementation capability from underlying algorithms to AI applications.
Presenter Li Jin recommends that the first stage of taking the FDE route should start with AI Agent development and private or local deployment of models.
All Facts (5)
Teacher Li Jin introduced in a livestream class that the FDE concept is becoming hot in 2026.
50%UnverifiedTeacher Li Jin suggested an advanced FDE technical path: first do AI agent development, then go deeper into model fine-tuning, distillation and pretraining.
50%UnverifiedTeacher Li Jin pointed out that many companies do not lack the conditions for fine-tuning but are unwilling to do it, the core reason being that the difference in effect before and after fine-tuning is hard to verify; sometimes the effect actually gets worse after fine-tuning, and hiring one person specifically to do fine-tuning can cost several hundred thousand a year.
50%UnverifiedTeacher Li Jin's research direction over the past two years has been to deeply combine traditional microservices with multi-agent systems and RAG retrieval, with end-to-end implementation capability from underlying algorithms to AI applications.
50%UnverifiedPresenter Li Jin recommends that the first stage of taking the FDE route should start with AI Agent development and private or local deployment of models.
50%