Middle AI & LLM Engineer

Role overview Develop retrieval-augmented generation pipelines, AI assistants and agent-based applications using hosted and open language models. The work spans document handling, retrieval design and answer-quality evaluation, with ownership of features from planning through production.

Responsibilities - Build RAG pipelines and AI assistant or agent features in Python. - Integrate hosted model APIs and work with open models. - Implement retrieval using embeddings and vector search. - Design prompts and assess the quality of generated answers. - Support document ingestion and processing, including PDFs and OCR. - Own feature delivery from design through production.

Requirements - 2–4 years of commercial experience in AI or LLM engineering. - Python experience and familiarity with the LLM ecosystem. - Knowledge of model APIs, such as OpenAI or Anthropic, and open models. - Practical understanding of embeddings, vector search and prompt design. - Experience evaluating answer quality and handling documents, including PDF and OCR workflows. - Good written English; Russian or Uzbek is a plus.

Benefits and work setup - Remote-first work, with the option of a hybrid arrangement in Tashkent. - Work on AI assistants, private language-model and retrieval systems, and enterprise software. - Salary set in USD according to experience. - Join a small, experienced team and work directly with its leadership.