Senior Prompt Engineer-Data Science & Quality Analysis

B.S. or higher in Data Science, Computer Science, Engineering, Linguistics, Philosophy, Cognitive Science, or related field. 5+ years of relevant experience with a B.S. degree, or 3+ years of experience with a Master’s degree. Proficiency in Python for automation, evaluation, and experimentation with LLM workflows. Proven experience in prompt engineering and working with LLMs (GPT-4, Claude, Gemini, LLaMA) for text generation, reasoning, and structured data extraction. Proficiency in Python and SQL for data analysis, evaluation scripting, and workflow automation. Strong background in A/B testing, statistical analysis, and performance metrics evaluation. Familiarity with prompt-evaluation tools (e.g., LangFuse, Galileo) and experiment management tools (e.g., Weights and Biases). Deep understanding of advanced prompting techniques. Experience applying specific prompting frameworks (CO-STAR, TIDD-EC!). Excellent requirement-elicitation and communication skills. Analytical mindset with a process-driven approach.

Design, test, and optimize LLM prompts for various AI tasks. Build evaluation pipelines to analyze prompt performance. Conduct prompt experiments and regression testing. Collaborate with teams to translate business objectives into prompt-engineering strategies. Use Python/SQL to analyze model outputs and automate quality checks. Document best practices for prompt evaluation. Communicate findings to stakeholders to drive business impact.