Machine Learning Benchmark Task Designer

IXO is engaging specialists to evaluate machine-learning coding tasks with realistic data and verifiable results. Your contribution is technical work: make the reasoning inspectable, identify substantive errors and provide evidence that supports a reliable assessment.

Work you will do

• Construct or assess Python-based modeling and evaluation tasks for AI engineering systems.
• Develop a correct reference approach and inspect the data, metrics and implementation assumptions that govern the result.
• Provide reproducible checks and clear technical explanations for important errors or alternative solutions.

Required background and routes

• A master's or PhD in computing, ML, AI, engineering, mathematics, statistics or a related quantitative subject, with strong professional or research ML experience.
• Practical Python and coding-agent skills, using suitable tools such as JAX, PyTorch, SciPy/NumPy, vLLM, SGLang, llama.cpp or Hugging Face models/tokenizers; equivalent relevant tools are acceptable.

Preferred background

• Experience in an established engineering or AI research organization. Exceptional academic or open-source work can also qualify.

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 15 hours per week depending on the track. IXO confirms the applicable timing before work.

Pay and working terms

Per completed task; fee agreed before work USD. Payment is for a completed task that meets the agreed acceptance criteria. The fee, task specification and revision requirements are agreed before work; an advertised time estimate does not determine payment. 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.