About Us
We are building an AI-powered product to support SAT students in Iran. Our platform leverages cutting-edge Large Language Models (LLMs) to deliver personalized, effective, and engaging learning experiences. The project is already 95% LLM-driven, so this role is central to our success.
Responsibilities
- Develop, fine-tune, and optimize LLMs for education-focused use cases.
- Design and implement workflows for prompt engineering, evaluation, and continuous improvement.
- Build scalable pipelines for model training, inference, and deployment.
- Integrate LLMs with our product (e.g., tutoring, test prep, personalized study plans).
- Monitor performance, accuracy, and reliability of LLM-based features.
- Stay up to date with the latest research and advancements in LLMs and generative AI.
Requirements
- Hands-on experience working with LLMs (e.g., GPT, LLaMA, Claude, Mistral, or similar).
- Strong Python programming skills and familiarity with ML frameworks (PyTorch, TensorFlow, Hugging Face).
- Problem-solving mindset with ability to work independently and in a team.
- Experience in fine-tuning, RAG (Retrieval-Augmented Generation), or model evaluation.
- Understanding of prompt engineering and system design for LLM applications.
Nice to have experience with educational technology or test-prep products.