About the job
LILT is creating a worldwide network of specialized experts to enhance the quality of AI evaluations across various stages including training, benchmarking, red-teaming, and ongoing model monitoring. We invite finance and investment professionals to lend their expertise to our human-in-the-loop AI evaluation processes, utilized by prominent enterprises and hyperscalers.
This position is ideal for individuals who comprehend how financial, investment, and economic data inform real-world decision-making and can leverage that knowledge to evaluate, analyze, and enhance multilingual AI systems.
Your insights will significantly impact the quality, safety, and readiness for deployment of our multilingual AI models.
This role encompasses two distinct expert tracks based on experience and responsibilities.
Track A: Finance & Investment AI Rater
Raters carry out structured evaluations following explicitly defined rubrics and guidelines.
Responsibilities
Evaluate AI outputs related to financial, investment, and economic content
Perform structured scoring, comparison, classification, and judgment tasks
Assess factual accuracy, numerical correctness, relevance, and risk factors
Identify inaccuracies, misleading financial advice, unsupported claims, or regulatory issues
Consistently apply domain-specific financial guidelines across evaluations
Ideal Background
Professionals with backgrounds in finance, investment analysis, economics, accounting, auditing, or financial research
Experience interpreting financial statements, investment documents, market data, or economic analyses
Meticulous attention to detail and familiarity with structured evaluation criteria
Track B: Finance & Investment AI Evaluator (Senior Track)
Evaluators provide higher-level oversight and influence evaluation methodologies.
Responsibilities
Validate and enhance evaluation rubrics and edge-case methodologies
Resolve discrepancies among raters through adjudication
Conduct error analyses and qualitative reviews of model performance
Collaborate with LILT's research, product, and community teams to ensure comprehensive evaluations

