Təsvir

• Develop and fine-tune transformer-based models specifically for the Azerbaijani language.
• Work with Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) systems to enhance AI-driven capabilities.
• Contribute to the development of AI applications, improving the accuracy and efficiency of language models and related technologies.
• Develop and optimize Retrieval-Augmented Generation (RAG) systems for improving information retrieval and response generation.
• Design and optimize algorithms for entity recognition, text summarization, and semantic search.

Tələblər

• 2+ years of professional experience in Data Science with a strong focus on NLP and LLM applications.
• Hands-on experience building and deploying LLM-powered chatbots, mainly in on-premise environments.
• Strong knowledge of RAG systems: document chunking, embeddings, retrieval strategies, and vector databases (FAISS, Pinecone, Weaviate).
• Practical experience with Azerbaijani NLP tasks: classification, NER, sentiment analysis, text generation, and translation.
• Solid understanding of transformers and foundation models (BERT, GPT, T5, LLaMA, etc.).
• Experience with LLM evaluation, testing, and prompt optimization.
• Proficient in PyTorch, TensorFlow, Hugging Face ecosystem, and embedding-based similarity search.
• Expertise in LLM optimization (LoRA, quantization, distillation) for efficient on-prem deployment.
• Experience with LLM serving frameworks (vLLM, Ollama, TGI) and RAG/agent frameworks (LangChain, LlamaIndex).
• Skilled in CI/CD for ML, model tracking (MLflow/W&B), Docker, Kubernetes, and monitoring.
• Familiar with secure and compliance-heavy environments (public sector, healthcare, finance).

Vakansiya növü - Tam ştat

Maraqlanan namizədlər Müraciət et düyməsində qeyd olunan linkə daxil olaraq müraciət edə bilərlər.