Remote ML Benchmark Evaluator & Task Designer

ixolabs.ai; France; Sur place; EUR 180 000 - 192 000; Plein temps

Résumé du poste

IXO is seeking contributors to design realistic ML research tasks and write reference solutions with grading rubrics. You will validate that the task measures meaningful capabilities by evaluating outputs with actual training or evaluation code and documented reasoning.

Required: hands-on ML research, first-author ML paper, and a relevant master's or PhD. Remote assignments are scheduled flexibly with 5-40 hours per week as needed.

Qualifications

• Hands-on ML research experience required.
• First-author ML paper in ML or closely related field.
• Practical training, evaluation or systems code required; annotation-only experience is insufficient.

Responsabilités

• Design realistic research tasks within ML specialties you know in depth.
• Write reference solutions and grading rubrics, and validate that the task measures a meaningful capability.
• Evaluate outputs using actual training, evaluation or systems code and documented reasoning.

Formation

Master's or PhD in ML or related field

Description du poste

IXO is seeking contributors to design realistic ML research tasks and write reference solutions with grading rubrics. You will validate that the task measures meaningful capabilities by evaluating outputs with actual training or evaluation code and documented reasoning.

Required: hands-on ML research, first-author ML paper, and a relevant master's or PhD. Remote assignments are scheduled flexibly with 5-40 hours per week as needed.