AI Engineering

Support the development and testing of agentic architecture components using LangGraph and MCP Participate in LLM evaluation methodology and result analysis Learn how AI response quality, accuracy, and safety are assessed Test and improve Speech-to-Text (STT) and Text-to-Speech (TTS) components Optimize prompts, test dialogue scenarios, and identify system issues Collaborate with cross-functional business and technical teams
3rd or 4th year bachelor’s student or recent graduate Basic knowledge of LLMs (OpenAI, Claude, or similar) Basic understanding of agentic systems, LangGraph, or MCP Familiarity with LLM evaluation concepts Interest in speech technologies Basic knowledge of Python and SQL

