Note: The job is a remote job and is open to candidates in USA. 24-MAG LLC makes this opportunity available through its platform; the hiring client is not identified. The role focuses on applied research into financial AI, developing evaluation frameworks and benchmarks, analyzing model performance, and collaborating with research, engineering, product, and finance stakeholders.

Responsibilities

• Design, develop, and evolve evaluation frameworks for AI systems operating across financial domains
• Build benchmark suites, scoring methodologies, quality rubrics, and research-grade evaluation protocols
• Conduct applied research into financial reasoning, decision-making, and workflow automation
• Translate research findings into measurable improvements in AI system performance
• Define rigorous methods for assessing financial intelligence across complex enterprise use cases
• Develop and curate datasets, test cases, and benchmark environments representing real-world enterprise finance challenges
• Translate ambiguous financial problems into measurable research questions and evaluation criteria
• Design assessment scenarios covering complex financial reasoning and decision-making workflows
• Establish appropriate performance standards for finance-focused models and agentic systems
• Support the development of repeatable and scientifically robust evaluation processes
• Analyse AI model behaviour, failure modes, reasoning patterns, and performance trends
• Identify weaknesses and opportunities for improvement across finance-focused models and agentic workflows
• Develop analytical methodologies for evaluating model performance across financial tasks
• Produce actionable research insights that can guide future experimentation and research priorities
• Incorporate emerging techniques from AI evaluation, machine learning, financial modelling, and agent architectures into research initiatives
• Collaborate closely with AI researchers, machine learning engineers, product professionals, and other research stakeholders
• Produce internal research reports, technical documentation, methodological guidance, and best-practice materials
• Contribute to research standards for enterprise financial intelligence and AI evaluation
• Share findings clearly with both technical and finance-focused audiences
• Support a distributed research environment centred on scientific rigour, experimentation, and collaborative problem-solving

Skills

• Advanced degree in Finance, Economics, Financial Engineering, Quantitative Finance, or a closely related discipline
• MBA, CFA, or equivalent advanced professional expertise may also be considered
• Deep domain expertise in one or more areas including investment research, capital markets, risk management, corporate finance, accounting, or financial analysis
• Demonstrated experience conducting rigorous research, developing analytical methodologies, or building evaluation frameworks
• Strong ability to convert complex or ambiguous financial problems into measurable research questions and assessment criteria
• Exceptional analytical, quantitative, and critical-thinking skills
• Excellent written and verbal communication skills, including experience producing research reports, technical documentation, or thought-leadership materials
• Experience working across research, engineering, product, and other cross-functional teams
• PhD
• Experience evaluating or benchmarking large language models, AI agents, reasoning systems, or enterprise AI applications
• Familiarity with agentic workflows, synthetic data generation, AI evaluation methodologies, or model-alignment techniques
• Publication history in academic research, industry research, or recognised technical publications
• Proficiency with quantitative research and data-analysis tools such as Python, SQL, statistical-analysis environments, or machine-learning frameworks

Benefits

• Fully remote

Company Overview