Published ML Benchmark Researcher

IXO is engaging specialists to evaluate machine-learning research benchmarks written by people who publish and implement the methods. Your contribution is technical work: make the reasoning inspectable, identify substantive errors and provide evidence that supports a reliable assessment.

Work you will do

• Design realistic research tasks within the 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 scientific reasoning; annotation-only experience does not replace the required research practice.

Required background and routes

• At least one year of hands-on ML research, a first-author research paper in ML or a closely related field, and a relevant master's/PhD completed or underway.
• Practical training, evaluation or systems code is required; annotation-only experience is insufficient.

Preferred background

• Multiple first-author papers or measured improvements over baselines, recognized ML venues and deep expertise in at least one task area rather than superficial breadth.

Deliverables

Submit the completed technical artifact or assessment with its supporting evidence, explicit assumptions, reproducible checks where applicable, and concise reasons for each material judgment. Address review findings within the agreed scope.

Location and schedule

Remote assignments are scheduled by agreement, with no guaranteed weekly volume. Availability planning can include 5-40 hours per week depending on the track. IXO confirms the applicable timing before work.

Pay and working terms

$150 $160/hr USD. The agreed hourly rate, scope, schedule and acceptance criteria are confirmed before work starts. Applying does not guarantee an assignment. Use public, licensed or otherwise authorized material only; do not submit confidential employer information, personal data or restricted research.