The company is looking to solve the problem of designing and crafting conversational prompts and responses for state-of-the-art AI experiences, specifically for AI productivity tools used by millions, with a focus on prompt evaluation, automation, and ensuring seamless interaction between users and AI systems at Randstad Digital.
Requirements
- Proficiency in Python or C-Sharp for coding and automation tasks.
- Experience with LLM prompt engineering and evaluation systems.
- Strong foundation in computer science, including data structures and algorithms.
- Ability to manage and ingest complex datasets for AI training and testing.
- Prior experience in data science or experimentation.
- Experience with synthetic data generation and grounding data.
Responsibilities
- Develop and maintain a library of pre-defined prompts for various scenarios and user needs.
- Setup synthetic tenant data and automate the creation of test datasets for AI evaluation.
- Integrate quality checks into software build and deployment pipelines.
- Analyze system requirements and develop software solutions to meet client needs.
- Perform unit testing, quality assurance reviews, and post-implementation validation.
- Iterate with engineering teams to inspect results and improve AI response quality.
Other
- Bachelors degree
- 2-4 years of experience in software design and development.
- Degree in Computer Science, Computer Engineering, or a related field.
- Travel is not mentioned, but work hours are 8am to 5pm
- Equal Opportunity Employer: Race, Color, Religion, Sex, Sexual Orientation, Gender Identity, National Origin, Age, Genetic Information, Disability, Protected Veteran Status, or any other legally protected group status.
