Luciqo.ai
AI Evaluation and Statistical Assurance Specialist
How your CV stacks up
Upload your CV to see how well it fits this job role
?%
About the opportunity
Luciqo AI is seeking an experienced independent specialist to lead the statistical evaluation, confidence validation and bias testing for an ambitious 12-month research and development project.
This subcontract opportunity would suit an Applied Statistician, AI Evaluation Scientist, Data Scientist specialising in experimental design, Responsible AI Specialist, Algorithmic Assurance Specialist or academic research consultant.
The successful subcontractor will independently assess the project’s methods and results, ensuring that its findings are statistically reliable, transparent and supported by robust evidence.
Key responsibilities
The subcontractor will:
- Design an independent statistical evaluation methodology and testing framework.
- Translate the project’s research hypotheses into measurable evaluation criteria.
- Calculate appropriate sample sizes and statistical power requirements.
- Define suitable control groups, baselines and comparison methods.
- Test the repeatability and variability of outputs across multiple runs.
- Assess differences between AI model providers and model versions.
- Validate the methodology used to calculate confidence scores.
- Determine whether confidence scores accurately reflect the reliability of the underlying evidence.
- Measure false-positive and false-negative rates.
- Test for bias and uneven performance across different sectors, company sizes, locations and AI model providers.
- Identify potential sampling, measurement and methodological biases.
- Define appropriate statistical significance thresholds and uncertainty measures.
- Review the quality, limitations and representativeness of the controlled research dataset.
- Independently verify whether the research hypotheses have been supported.
- Produce clear findings, recommendations and assurance documentation.
- Contribute evidence suitable for the project’s final evaluation and dissemination.
Reasons to use Rodeo
Start with a chat, not a search bar
Grad scheme, placement, apprenticeship? Not sure what you want yet — that's fine. Your agent talks it through with you and turns "I have no idea" into a shortlist.
It searches the market for you
Every day your agent scans the market matching roles against what actually matters to you, not just keywords on a CV.
Only hits
No noise. No "maybe this fits." Just roles with a clear explanation of why they're right — and where to focus when applying.
Essential experience
Candidates should demonstrate:
- Strong experience in applied statistics, data science, experimental design or AI evaluation.
- Experience designing robust research and evaluation methodologies.
- Knowledge of statistical power, sample-size calculations and hypothesis testing.
- Experience assessing repeatability, variability, confidence and uncertainty.
- Understanding of false positives, false negatives, precision, recall and related evaluation measures.
- Experience testing bias, fairness or differential performance across groups.
- Ability to work with complex datasets and outputs generated by multiple AI models.
- Strong analytical reporting and research-documentation skills.
- Ability to provide an independent and objective assessment of project findings.
- Excellent written and verbal communication skills.
Desirable experience
The following would be advantageous:
Get help with your application
Your very own career expert that helps elevate your application to the next level.
- Experience evaluating generative AI, large language models or AI recommendation systems.
- Knowledge of responsible AI, algorithmic assurance or model-risk management.
- Experience validating confidence-scoring or probabilistic systems.
- Experience working with knowledge graphs, evidence graphs or provenance data.
- Experience publishing or reviewing academic research.
- Familiarity with Python, or comparable statistical-analysis tools.
Expected deliverables
Indicative deliverables will include:
- Statistical evaluation plan and methodology.
- Sample-size and statistical-power assessment.
- Repeatability and variability testing framework.
- Confidence-score validation report.
- False-positive and false-negative analysis.
- Cross-sector, company-size, location and model-provider bias assessment.
- Independent review of the research hypotheses and supporting evidence.
- Final statistical evaluation and assurance report.
- Practical recommendations for improving the methodology and Luciqo AI platform.
Contract arrangement
- Engagement type: Independent subcontractor
- Project duration: Up to 12 months
- Location: United Kingdom preferred; remote delivery considered
- Start date: Subject to project funding and final agreement
Applicants may be independent consultants, academic research specialists or specialist organisations with relevant expertise.
“It took my CV and asked me questions relevant to understanding what kind of jobs to suggest for me. Suggestions were almost perfect. Jobs were exactly what I’ve been looking for.”
Jessica, London
Skills
Location