חזרה

Junior Prompt Engineer - AI Research & Reliability

Gong
שכר לא צויןTel Aviv, היברידיג׳וניורמשרה מלאה
משרה חיצונית, ההגשה באתר החברהאושר שהמשרה פתוחה לפני 13 שעות

You will test, refine, and evaluate prompts and AI workflows for Gong products, working with product teams, data scientists, and engineers. Your work will help improve AI accuracy, reliability, and user-facing experiences.

מה תעשו

  • Craft, test, and refine prompts for Gong applications, including Gong Assistant.
  • Assist with multi-agent systems, tool-retrieval workflows, memory mechanisms, and execution paths.
  • Evaluate prompt performance using test datasets, benchmarks, and user feedback.
  • Run experiments on prompting techniques and updates in NLP and generative AI.
  • Document prompt structures, evaluation results, and system behavior.

דרישות

  • Hands-on experience with LLMs and prompt design through internships, academic or personal projects, or 1–2 years of professional experience.
  • Basic working knowledge of AI development frameworks or agentic concepts, such as LangChain, LlamaIndex, LLM APIs, or RAG pipelines.
  • Proficiency in Python or a similar language for automated testing, evaluation, and data processing.
  • A methodical approach to problem-solving, experimentation, and measuring results.
  • Strong communication skills and ability to collaborate across engineering, product, and data science teams.
LLMsPrompt EngineeringPythonLangChainLlamaIndexRAGAI Evaluation