Remote Knowledge Engineer

Summary

Join Prompt as a Knowledge Engineer on our internal AI team to ensure the quality, consistency, and ethical standards of our AI solutions. You will review AI inputs and outputs, research ethical guidelines, and collaborate across teams to enhance documentation and testing processes.

Requirements

• Bachelor’s degree in Computer Science, Data Science, Communication, English, Ethics, or a related field. Master’s preferred
• Demonstrated ability to analyze information and ensure quality assurance
• Strong proficiency in English, with excellent written and verbal communication skills
• Familiarity with AI technologies and methodologies, particularly in natural language processing (NLP)
• Strong problem-solving skills and attention to detail
• Experience with creating and reviewing technical documentation
• Self-motivated and capable of working independently as well as collaboratively in a team environment
• Ability to work collaboratively in a fast-paced, team-oriented environment
• Strong problem-solving skills and attention to detail
• A passion for continuous learning and staying updated on AI advancements and best practices

Responsibilities

• Review AI inputs and outputs to assess: Input quality and consistency Output quality and consistency Potential biases in AI algorithms
• Research and codify ethical guidelines and concerns specific to various AI use cases
• Develop test datasets to ensure adherence to established ethical guidelines
• Create and review AI documentation for diverse stakeholders, including: User instructions for end-users Internal and external best practice guides Semi-technical reports for management on project statuses Sales materials to communicate new AI features to prospective customers Blog articles establishing AI thought leadership within the industry Comprehensive documentation for the AI codebase, including: Assisting with ReadMe files Identifying missing information for developers to address Reviewing and updating content on the AI Docs Website
• Evaluate LLM datasets for quality and accuracy, including: Creating and reviewing test datasets for high-quality testing Creating and reviewing training datasets to ensure optimal training conditions
• Review processed documentation for adherence to the ground truth, especially in the context of re-written help articles for RAG use cases
• Monitor production LLM use cases and generate tickets for AI engineers to facilitate improvements
• Generate reports on the performance of production LLM use cases and identify areas for enhancement

Benefits

• Competitive salaries
• Remote/hybrid environment
• Potential equity compensation for outstanding performance
• Flexible PTO
• Company-wide sponsored lunches
• Company paid disability and life insurance benefits
• Company paid family and medical leave
• Medical, dental, and vision insurance benefits
• Discounted pet insurance
• FSA/DCA and commuter benefits
• 401k