استخدام Mid Level) ML Engineer)

We are building an innovative AI-based personal adaptive tutor designed to revolutionize learning in programming and scientific disciplines. Our mission is to create a truly personalized and engaging educational experience, leveraging cutting-edge AI including Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and multi-agent systems. A key aspect of our platform is comprehensive bilingual support (English and Farsi). We are an early-stage venture offering a unique opportunity to shape a transformative educational product from the ground up.

We are seeking a highly skilled and experienced Senior AI Engineer to lead the design, development, and optimization of the core artificial intelligence engine powering our adaptive tutor. You will be instrumental in architecting and implementing the ML/AI components that enable personalized learning paths, intelligent interaction, and dynamic content generation. This is a hands-on role with significant impact, reporting directly to the product manager.

●     Design, build, iterate, and optimize the core multi-agent AI engine responsible for user interaction, learning evaluation, and adaptation.

●     Develop and implement sophisticated Retrieval-Augmented Generation (RAG) pipelines, including selecting/managing embedding models, vector databases (e.g., Pinecone, Milvus, Chroma), and retrieval strategies.

●     Integrate with state-of-the-art external LLM APIs (e.g., OpenAI, Anthropic, Google) for initial prototyping and MVP development.

●     Lead the strategy and execution for evaluating, selecting, fine-tuning (including PEFT methods like LoRA/QLoRA), and deploying open-source LLMs for enhanced customization, cost-efficiency, and specialized tasks (including potential Farsi language adaptation).

●     Research, design, and implement algorithms for tracking user learning curves, identifying knowledge gaps, and dynamically personalizing learning content and delivery methods.

●     Apply strong NLP techniques for effective text understanding, generation, and potentially voice interaction (Speech-to-Text/Text-to-Speech).

●     Collaborate closely with backend and frontend engineers to ensure seamless integration of AI features into the overall platform.

●     Stay abreast of the latest advancements in AI, LLMs, RAG, and related fields, advocating for and applying relevant innovations.

●     Contribute to best practices for MLOps, including model testing, deployment, monitoring, and lifecycle management in a cloud environment.

●     Potentially mentor future junior AI/ML team members.

●     MSc or PhD in Computer Science, Artificial Intelligence, Machine Learning, or a related quantitative field, OR equivalent practical experience.

●     3+ years of professional experience in designing and implementing AI/ML models and systems in production environments.

●     Strong proficiency in Python and common ML libraries/frameworks (e.g., PyTorch, TensorFlow, Hugging Face Transformers, Scikit-learn, LangChain/LlamaIndex).

●     Deep understanding and hands-on experience with Large Language Models (LLMs), including both API integration and working with open-source models.

●     Proven, practical experience in designing and building RAG systems.

●     Demonstrable experience in fine-tuning LLMs; experience with PEFT techniques (LoRA, QLoRA, etc.) is highly desirable.

●     Solid foundation in Natural Language Processing (NLP) principles and applications.

●     Experience deploying and managing ML models in a major cloud environment (AWS, GCP, or Azure).

●     Experience designing or working with multi-agent AI systems.

●     Experience with Farsi NLP tasks or models.

●     Experience integrating Speech-to-Text (STT) and Text-to-Speech (TTS) technologies.

●     Excellent analytical and problem-solving skills.

●     Strong communication and collaboration skills, with the ability to explain complex technical concepts clearly.