Job Summary: Develop AI solutions based on LLMs, including RAG; design data and inference pipelines; and work in an agile environment focused on prompt optimization. Key Highlights: 1. LLM and RAG-based solution development 2. AI API development with FastAPI and model integration 3. Agile environment work following SCRUM practices Develop LLM-based solutions, including RAG (Retrieval-Augmented Generation). Design and implement indexing, retrieval, and information ranking pipelines. Create and optimize prompts to ensure response quality, consistency, and security. Build AI APIs using FastAPI. Integrate language models into existing systems. Develop and maintain data and inference pipelines. Evaluate and monitor the performance of AI systems in production. Work in an agile environment following SCRUM practices. **Responsibilities** Develop LLM-based solutions, including RAG (Retrieval-Augmented Generation). Design and implement indexing, retrieval, and information ranking pipelines. Create and optimize prompts to ensure response quality, consistency, and security. Build AI APIs using FastAPI. Integrate language models into existing systems. Develop and maintain data and inference pipelines. Evaluate and monitor the performance of AI systems in production. Work in an agile environment following SCRUM practices. **Requirements:** Strong foundation in Statistics and Linear Algebra applied to Machine Learning. Proficiency in Python, with emphasis on software engineering. Solid knowledge of Python Design Patterns. Experience with SQL and Database Management Systems. Ability to handle structured and unstructured data. Experience with Docker. Proficiency in Git usage. Experience developing APIs with FastAPI. Knowledge of NLP. Practical experience with LLMs. Experience with RAG (Retrieval-Augmented Generation). Knowledge of Prompt Engineering (prompt design, evaluation, and optimization). Experience with AI orchestration frameworks: LangChain LangGraph CrewAI **Preferred Qualifications:** Experience with search and ranking systems: TF-IDF BM25 Knowledge of Solr, Lucene, and/or Elasticsearch. Experience with MoreLikeThis (Lucene). Knowledge of search and retrieval evaluation metrics: MAP NDCG Precision@k Recall@k MRR Experience with recommendation systems. Experience with deep neural networks. Familiarity with BERT and similar models. Experience with model deployment, versioning, and monitoring. ### **Employment Type:** CLT ### **Benefits:** Health insurance, Dental insurance, Meal voucher, Food allowance, others ### **Department:** Operations