We are looking for a passionate AI Engineer with expertise in AI Agents, Natural Language Processing (NLP) and Large Language Models (LLMs) to join our team(one of alibabagroup business). You will play a central role in developing and fine-tuning AI models for our AI-powered Legal Assistant, focusing on tasks such as RAG, NER, text classification, information retrieval, and legal document understanding.
This is a unique opportunity to work on cutting-edge AI applied to real-world judicial and legal challenges.

Responsibilities:

• Design, train, and fine-tune NLP/LLM models for legal and judicial text.
• Work with annotated legal datasets to develop high-quality models for NER, summarization, and classification.
• Collaborate with Data Engineers to prepare and preprocess large-scale text datasets.
• Integrate models into production systems in collaboration with Backend and MLOps engineers.
• Evaluate models using robust metrics and continuously improve their performance.
• Build AI Agents and MCP servers to enable autonomous task execution.
• Research and experiment with state-of-the-art methods in transformers, RAG, embeddings, and LLM fine-tuning.
• Ensure model fairness, reliability, and compliance with privacy/security requirements.

Requirements:

• Strong programming skills in Python (PyTorch, TensorFlow, Hugging Face Transformers).
• Solid experience in NLP tasks (NER, text classification, summarization, semantic search).
• Hands-on experience with LLM fine-tuning and prompt engineering.
• Familiarity with vector databases (e.g., Pinecone, Weaviate, FAISS, Qdrant).
• Understanding of retrieval-augmented generation (RAG) architectures.
• Knowledge of MLOps practices for deploying and monitoring ML models.
• At least 3 years of experience in NLP, ML, or AI engineering roles.

Nice to Have:

• Experience working with legal or domain-specific text datasets.
• Familiarity with Persian (Farsi) NLP models (e.g., ParsBERT, HooshvareLab BERT, mBERT, XLM-R) for NER tasks.
• Knowledge of Spark NLP for large-scale text processing and de-identification.
• Experience with multi-lingual NLP and low-resource language adaptation.
• Research background with publications or contributions to open-source NLP projects.

Benefits:

• Be part of an innovative and impactful project at the intersection of AI and the legal system.
• Work with a talented cross-functional team (Data, Backend, MLOps, Product, UX).
• Growth opportunities in LLMs, generative AI, and applied NLP research.
• Flexible work setup and a collaborative environment.