Remote Manual Testing Jobs in New York (NOW HIRING)

Specialised Full-Time Consulting Opportunity for Data Scientists and Quantitative AnalystsWe are sharing a specialised full-time consulting opportunity for experienced data scientists and quantitative analysts with strong expertise in statistical analysis, data cleaning, method comparison, reproducible research, and evidence-based reporting.This role supports the development of advanced agentic evaluation benchmarks for frontier AI models. Selected professionals will create realistic data-analysis challenges, develop reproducible reference notebooks, evaluate model-generated analyses, and identify where statistical reasoning, interpretation, or reporting falls short of professional standards.Key ResponsibilitiesData Analysis Task DesignCreate realistic analytical tasks based on professional data science and quantitative research workflowsDevelop assignments involving messy data, anomaly detection, correlation analysis, hypothesis testing, and method comparisonDesign complex, multi-step problems requiring statistical judgment and careful interpretationEnsure tasks include realistic constraints, datasets, assumptions, and decision-making objectivesReproducible Notebook DevelopmentComplete reference analyses using Jupyter Notebook or Google ColabBuild clear and reproducible workflows using Python, pandas, NumPy, and related librariesDocument data-cleaning decisions, calculations, statistical methods, and analytical conclusionsValidate intermediate results, spot checks, visualisations, and final recommendationsStatistical Method ComparisonDesign fair comparisons between analytical models, algorithms, or statistical approachesEvaluate performance using appropriate metrics, manual checks, and sensitivity analysesIdentify methodological trade-offs, limitations, and sources of uncertaintyProduce recommendations supported by transparent quantitative evidenceAI Model EvaluationReview model-generated analyses for statistical accuracy, methodological rigour, and sound interpretationVerify whether calculations, correlations, hypotheses, and conclusions are supported by the dataIdentify coding errors, unsupported assumptions, misleading summaries, and analytical shortcutsExplain where and why model outputs fail to meet professional data-analysis standardsResearch CollaborationWork closely with researchers, task authors, and fellow quantitative specialistsCompare evaluation decisions to maintain consistent benchmark standardsRefine tasks, reference notebooks, and grading criteria based on testing outcomesDocument recurring model weaknesses and opportunities for stronger evaluation coverageIdeal ProfileStrong candidates may have:At least 1 year of experience in data science, quantitative analysis, research engineering, or another research-intensive analytical roleDeep hands-on experience with data cleaning, statistical correlation, hypothesis testing, and interpretationStrong proficiency in Python, including pandas, NumPy, or comparable analytical librariesExperience using Jupyter Notebook or Google Colab for analysis and reportingWorking familiarity with Git and reproducible analytical workflowsAbility to communicate complex quantitative findings clearly to technical and non-technical decision-makersStrong attention to detail and confidence working through ambiguous, open-ended problemsReliable availability for approximately 35 hours per weekEducational BackgroundA master's degree or PhD in statistics, data science, mathematics, economics, computer science, engineering, or another quantitative discipline is highly relevantEquivalent practical experience in a research-heavy analytical field may also be consideredAcademic or professional research involving statistical modelling, experimentation, or large-scale data analysis may strengthen an applicationPublications, technical reports, open-source work, or impactful analytical projects may also be valuableNice to HaveExperience in AI training, model evaluation, or benchmark developmentBackground authoring analytical tasks, reference solutions, or grading rubricsFamiliarity with anomaly detection, experimental design, or comparative model evaluationExperience conducting manual spot checks and validating automated analysesKnowledge of statistical modelling, machine learning, or scientific computingFamiliarity with agentic AI systems and multi-step model evaluationsExperience reviewing notebooks, code, or analyses prepared by other professionalsStrong ability to identify subtle statistical errors and unsupported conclusionsWhy This OpportunityApply advanced data science and quantitative analysis expertise to frontier AI evaluationDesign realistic tasks grounded in professional analytical workflowsHelp improve how AI systems reason through statistics, data quality, and method comparisonWork across Python, reproducible notebooks, model evaluation, and evidence-based reportingCollaborate closely with researchers and other quantitative specialistsParticipate in a structured full-time remote role with competitive hourly compensationContract DetailsFull-time W-2 contingent employment opportunityFully remote within the United StatesExpected commitment of approximately 35 hours per weekCompetitive rates between $55–$85 per hour depending on expertise and project scopeIndividual tasks may require one to two days of focused analysis and implementationWork may include task design, data cleaning, statistical analysis, notebook development, AI output evaluation, and technical reportingEngagement scope and duration may evolve according to project requirements and performanceThis opportunity is available through 24-MAG LLC. We connect experienced professionals with remote consulting opportunities across technical, evaluation, and project-based workstreams.By submitting this application, you acknowledge that your information may be processed by 24-MAG LLC for recruitment and opportunity matching in accordance with our Privacy Policy.