Junior AI & LLM Engineer

Role overview Develop retrieval-augmented generation workflows, AI assistants, and agents using open or hosted language models. The work includes building document-aware systems and assessing the quality of their answers.

Responsibilities - Build RAG pipelines and AI assistant or agent features. - Integrate hosted model APIs or open models into applications. - Work with embeddings, vector search, and prompt design. - Process documents such as PDFs, including workflows that use OCR. - Evaluate answer quality and improve system behavior through iteration. - Learn through code reviews and mentoring from senior engineers.

Requirements - Up to two years of experience, or strong personal or university projects. - Python and familiarity with the LLM ecosystem, including hosted APIs or open models. - Understanding of RAG concepts such as embeddings and vector search. - Ability to design prompts and evaluate generated answers. - Experience handling documents such as PDFs; OCR familiarity is relevant. - Good written English; Russian or Uzbek is a plus, along with willingness to learn through feedback.

Benefits and work setup - Remote-first work, with a hybrid option in Tashkent. - Mentoring and code review from senior engineers. - Salary in USD based on experience, described as market-level.