SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Noodle is seeking a Prompt Systems Engineer to design, test, and continuously improve the prompts and system instructions powering Noodle's AI agents across enrollment, learning, and student support use cases. This is a hands-on role at the intersection of AI capability and educational effectiveness.
Key responsibilities include:
Prompt Design & Engineering: Write and iterate on system prompts and instruction sets for AI agents focused on student enrollment, learning, and retention. Translate complex educational and operational requirements into reliable agent behavior, including persona definition, tone, scope constraints, and multi-turn conversation logic. Design prompt architectures for multi-step workflows and RAG-augmented agents that draw from program-specific knowledge bases. Collaborate with engineering to configure and deploy agents through Noodle's AI orchestration platform.
Evaluation & Quality: Build and maintain evaluation frameworks to measure agent accuracy, hallucination rate, task completion, and alignment with learning objectives. Use Langfuse to monitor prompt performance in production, identify regressions, and prioritize improvements. Design red-teaming and adversarial testing protocols to surface edge cases. Establish prompt versioning practices and maintain a library of reusable prompt components.
Collaboration & Enablement: Partner with Noodle teams and university stakeholders to design and test agents, translating learning objectives and operational flows into prompt-level instructions. Work with enrollment and student success teams to tune agents for specific programs. Contribute prompt engineering guidelines and best practices documentation. Stay current with model capability changes across OpenAI, Anthropic, and other providers.
Required qualifications: 2+ years designing and iterating on prompts for LLM-powered applications in production. Deep familiarity with prompt patterns (few-shot examples, chain-of-thought, system vs. user roles, output formatting, tool-use prompting, RAG integration). Strong written communication skills. Experience building and running prompt evaluations with defined metrics and test cases. Comfort working across disciplines with engineers and faculty. Experience with LLM observability tools. Familiarity with LTI and LMS platforms (Moodle, Canvas, Instructure). Basic code reading/writing ability (JavaScript, Python). Knowledge of OpenAI or Anthropic APIs. Ability to thrive in ambiguity and iterate based on feedback.
