Job
Expert Talent Pool, Evals and Benchmarks (Associate)
Clera Clera offers roles in legal evaluation of AI systems and ML internship opportunities
Remote mid-level data/evaluation role designing and evaluating AI model benchmarks for human-data projects.
At a glance
- Deadline
- Location
- Remote
- Salary
- 30 – 60 USD / hour
- Paid
- Yes
- Employment type
- Full Time
- Minimum years of experience
- 5
- Listed
About this opportunity
Clera is building a specialist talent pool that supports human-data projects focused on evaluating AI models. As an Associate, you will contribute to the design and execution of assessments that measure model capabilities and support AI safety and capability research.
The role is fully remote and worldwide, with projects ranging from one week to several months. You’ll write test questions, develop rubrics, create reference answers, and grade outputs to documented criteria.
You’ll also analyze errors, compare models using the same prompts, validate benchmarks, and participate in small user studies related to ratings and model outputs.
This position is suitable for someone with up to five years of relevant experience in QA, assessment design, ML evaluation, or related fields, and who is comfortable using spreadsheets and possibly Python for data analysis.
What you get
- Fully remote work
- Competitive hourly pay: $30–$60 per hour
- Project-based duration from one week to several months
- Opportunity to contribute to AI safety and capability research
Responsibilities
- Write questions and tasks that test specific model capabilities
- Develop rubrics defining strong, partial, and poor answers
- Create reference answers and edge cases
- Grade model outputs against rubrics and explain scoring
- Analyze failed answers and document error patterns
- Compare multiple models using identical prompts
- Validate benchmarks and flag compromised questions
- Participate in small user studies evaluating ratings or interactions
Requirements
- Zero to five years of professional experience
- Experience in QA or test engineering, assessment design, psychometrics, UX research, data analysis, ML evaluation, or related areas
- Experience writing test cases, rubrics, or evaluation tasks
- Comfort using spreadsheets or Python for results organization and analysis
- Familiarity with evaluation tools such as Inspect, lm-eval-harness, HELM, or promptfoo is useful
- Clear written communication and ability to compare AI model outputs
How to apply
- Apply through the listing page or the official link provided by the posting.
- Ensure your resume highlights QA, evaluation design, and data analysis experience.
Ready to apply?
WorkInRwanda never asks for money to apply. If anyone does, report it. Report this listing
About Clera
Clera is involved in legal and artificial intelligence work, offering roles that blend EU law expertise with AI evaluation. The listings indicate remote opportunities available worldwide and focus on senior legal professionals with EU knowledge as well as entry-level ML work.
See everything from Clera