Prompt Systems Engineer

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Prompt Systems Engineer based in the United States.

• Design, write, iterate, test, and maintain system prompts and instruction sets for AI agents supporting student enrollment, learning, retention, and student services.
• Translate complex educational, operational, and business requirements into precise agent behavior, including personas, tone, scope constraints, fallback handling, and multi-turn conversation logic.
• Design prompt architectures for multi-step and chained agent workflows, including Retrieval-Augmented Generation (RAG) experiences using program-specific knowledge bases.
• Collaborate with engineering teams to configure and deploy agents through an AI orchestration platform, including primary prompts, secondary context, knowledge-base attachments, and embed definitions.
• Design conversational experiences involving learners, campus or support staff, and AI assistants working together.
• Build and maintain evaluation frameworks that measure agent accuracy, tone, hallucination rates, task completion, and alignment with rubric-based learning objectives.
• Use LLM observability platforms such as Langfuse to monitor production performance, identify regressions, and prioritize improvements.
• Develop red-team and adversarial testing approaches to uncover edge cases, risks, and failure modes before agents are deployed to learners.
• Establish prompt versioning practices and maintain a library of tested, reusable prompt components.
• Partner with product, learning, enrollment, student success, engineering, and university stakeholders to design, build, test, and continuously improve AI agents.
• Translate learning objectives, operational workflows, rubric assessments, and program-specific requirements into effective prompt-level instructions.
• Tune companion agents for individual programs and educational partner contexts.
• Develop and document prompt engineering guidelines, standards, and best practices for internal teams.
• Monitor changes in capabilities across OpenAI, Anthropic, and other model providers, proactively identifying opportunities, limitations, and risks.
• Contribute to prompt automation, evaluation, and testing workflows using lightweight code where appropriate.

• 2+ years of experience designing and iterating on prompts for production LLM-powered applications.
• Deep familiarity with prompt engineering patterns, including few-shot examples, system and user roles, reasoning-oriented prompting, output constraints, tool-use prompting, and RAG integration.
• Exceptional written communication skills, with the ability to express complex requirements clearly, precisely, and persuasively.
• Hands-on experience creating and running prompt evaluations, including defining metrics, developing test cases, analyzing results, and making data-informed improvement decisions.
• Ability to collaborate effectively across technical and non-technical disciplines, from discussing context windows and APIs with engineers to translating educational frameworks and learning objectives with faculty or learning specialists.
• Experience with LLM observability platforms such as Langfuse, Weights & Biases, or similar tools.
• Familiarity with Learning Tools Interoperability (LTI) and the integration of AI tools with learning management systems such as Moodle, Canvas, or Instructure.
• Experience with voice agents, multimodal prompting, or other emerging AI interaction modalities is a plus.
• Ability to read and write basic JavaScript or Python to support prompt automation, experimentation, and testing pipelines.
• Working knowledge of OpenAI, Anthropic, or comparable model-provider APIs.
• Strong analytical and problem-solving skills, with the ability to identify failure modes and continuously improve AI behavior.
• Ability to thrive in ambiguity, experiment rapidly, and incorporate user feedback into iterative improvements.
• Strong organizational and collaboration skills in a dynamic, rapidly evolving, team-based environment.
• A genuine interest in applying AI to improve learning, enrollment, student success, and educational experiences.
• Applicants must be legally authorized to live and work in the United States and must reside within the United States for the duration of employment.

• Competitive annual salary of $100,000–$120,000.
• Fully remote work, with the option to work from a New York City office.
• Company-provided computer and charger.
• 401(k) plan with company matching.
• Equity opportunities.
• Medical, dental, and vision insurance for employees and families.
• Mental health resources, including access to Headspace and Talkspace.
• Employer-paid life and disability insurance.
• Optional supplemental life,