Design realistic, multi-step finance and accounting tasks based on professional workflows such as FP&A, financial reporting, auditing, and reconciliations.
Develop objective grading criteria and evaluation standards to assess AI system performance consistently.
Create scenarios requiring financial judgment, analytical reasoning, and error identification, supported by materials like Excel spreadsheets and financial statements.
The client organization focuses on the development and evaluation of advanced AI systems, particularly for complex professional tasks. It brings together experienced finance and accounting professionals to establish evaluation standards and improve AI-driven solutions.
Leverage investment banking and financial modeling expertise to design realistic Excel-based tasks for AI evaluation.
Complete each assignment to establish reference solutions and develop objective grading rubrics.
Work independently on a flexible, remote schedule with immediate start and weekly task-based compensation.
This partner company is advancing AI evaluation in financial modeling by engaging experienced investment banking professionals. It offers a fully remote, flexible project-based workflow with a focus on independent work and data integrity.
Evaluate and annotate complex financial materials to support AI training.
Draft, review, and refine financial deliverables like pitchbooks and valuation models.
Assess AI-generated financial content and provide actionable feedback on accuracy and reasoning.
The client is developing next-generation AI systems focused on investment banking and financial analysis. Team size and culture details are undisclosed, but the project values practical financial expertise and collaborative remote work.
Write realistic Excel tasks derived from your own People Ops/HR work, including extending models, fixing broken ones, and building from a brief.
Complete each task yourself so a clear, correct answer exists.
Draft yes-or-no criteria that allow graders to mark any attempt consistently.
Aptura is an applied AI and data company that builds high-quality evaluation and training environments for AI systems. It works with frontier labs and independent contractors on a project basis, teaching AI to perform real professional work.
Conduct desk research and stakeholder engagement to outline solutions for labor migration in the long-term care sector.
Develop comparability methodology and competence-based assessment designs through desk analysis and interviews with key actors.
Produce and copyedit work products including one-pagers, presentations, concept notes, and project reports.
LaMP is a non-profit organization dedicated to creating right-respecting labor mobility opportunities for people from low-income countries. It works with multi-sector stakeholders to deliver innovative proof of concept solutions and establish evidence for policy influence.
Support HR and Legal leaders with forecast updates, purchase and headcount approvals, and data reconciliations.
Assist departments with forecasting and reconciliation, and support implementation of new FP&A and reporting software.
Validate data migrations, document financial processes, and identify automation opportunities to improve reporting efficiency.
LastPass delivers secure access essentials, helping individuals and organizations manage and protect access to AI, applications, and credentials from the browser. Trusted by over 100,000 businesses and millions of users, the company is a high-growth, collaborative, remote-first environment that values new ideas and supports employee growth.
Develop realistic FP&A tasks that test AI agents' analytical capabilities.
Build reference solutions with transparent formulas and documented assumptions.
Evaluate AI agents on financial data, identifying errors and unsupported conclusions.
Anyone AI is a company that develops realistic tasks to test AI agents' ability to analyze business performance and support financial planning. We are a remote-first team with flexible hours, fostering a collaborative and innovative culture.
Develop and maintain financial models for forecasting, budgeting, and long-term planning.
Analyze financial performance against budget and forecasts, identifying trends and providing actionable insights.
Prepare monthly and quarterly financial reports for management, highlighting variances and business drivers.
Nimble Gravity is a team of outdoor enthusiasts, growth hackers, data geeks, and technology nerds who help businesses and non-profits apply technology and AI to solve problems. The culture emphasizes collaboration, innovation, and making a meaningful impact for clients and social initiatives worldwide.
Create realistic accounting tasks covering bookkeeping, journal entries, accounts payable and receivable, bank reconciliations, and financial statement preparation.
Develop reference solutions with accurate calculations, supporting documentation, and clearly explained accounting treatment.
Evaluate AI agents on classifying transactions, reconciling accounts, correcting discrepancies, and preparing accounting reports.
Anyone AI is a company developing AI agents and uses domain experts to create evaluation tasks. It operates as a remote, project-based organization with flexible hours and a focus on expert-driven quality.
Kobie is a loyalty consulting and technology company that helps brands build lasting emotional connections with their consumers. Named a Top Workplace in the USA, we are a remote-first organization with a collaborative and growth-focused culture.
Own the company's budgeting, forecasting, and long-range financial planning processes.
Partner with executives across Product, Sales, Marketing, and Tech to translate complex financial data into actionable recommendations.
Build scalable financial processes, dashboards, and reporting automation to support rapid growth and board reporting.
RootstockLabs is a key contributor to Rootstock, Bitcoin's financial infrastructure for lending, yield, and onchain capital markets. They build and commercialize institutional infrastructure that turns Bitcoin into productive capital with a global, diverse team.
Writing realistic Excel tasks from your own equity research work, including extending and fixing models.
Working through each task yourself to establish a clear, correct answer.
Writing yes-or-no criteria precise enough to grade any AI attempt.
Aptura is an applied AI and data company working with frontier labs to train AI systems on real professional work. It builds high-quality evaluation and training environments that teach AI agents to produce work that can be used in daily workflows.
Own and evolve Oportun's revenue forecasting and lending portfolio planning capabilities.
Build sophisticated financial models and translate operating and credit trends into clear insights for senior leadership.
Partner with cross-functional teams to improve forecast inputs, identify risks, and support strategic decisions.
Oportun is a mission-driven financial services company that provides responsible credit, savings, and budgeting tools to help members build a better financial future. It is a Nasdaq-listed company with a fast-paced, high-bar culture focused on making a real impact for real people.
Design realistic, multi-step finance and accounting benchmark tasks across FP&A, reporting, audit, and reconciliations.
Build clear instructions and objective grading rubrics that enable consistent reviewer evaluation.
Prepare supporting materials like spreadsheets and financial statements, and review tasks for accuracy and gradability.
Jobgether is a talent matching platform that uses AI to connect candidates with employers and streamline the hiring process. The company operates as a lean, tech-driven team focused on fast, objective, and fair candidate evaluation.
Build integrated financial models for revenue, margin, opex and cash flow with scenario analysis.
Analyze results vs forecast, track SaaS metrics like ARR and NRR, and explain variances.
Partner with finance and business leaders to turn data into clear recommendations.
Redwood Software is the leading orchestration platform for the autonomous enterprise, helping organizations automate and orchestrate mission-critical business and IT processes. Backed by 30 years of experience and trusted by more than 50% of the Fortune 50, Redwood values teamwork, curiosity, and ownership.
Own the monthly financial rhythm for Sales, Professional Services, Customer Success, and Marketing: variance analysis, reforecasting, and stakeholder reviews.
Build commercial and unit-economics analytics like CAC/LTV, bookings vs. OTE, retention, and PS profitability.
Drive FP&A process improvement and experiment with AI-enabled automation to make reporting faster and smarter.
BlueCat provides intelligent network operations and automation solutions that help large enterprises keep their networks secure, reliable, and scalable. It is a global, PE-backed company known as a Great Place to Work, with a culture focused on collaboration, integrity, and innovation.
Own budget tracking and expense forecasts for assigned teams, partnering with Corporate FP&A and stakeholders.
Track open roles and hiring assumptions, building financial models for investment requests and resource allocation.
Analyze technology and AI usage costs to improve efficiency, and partner with Product and Engineering teams.
Thumbtack helps millions of people confidently care for their homes through a single app for repairs, maintenance, and improvements. With over 300,000 local service businesses across the U.S., they are a growing platform focused on innovation and collaboration.
Manage project budgets, client invoicing, collections, and vendor purchase orders.
Monitor financial performance, prepare burn reports, and escalate budget risks.
Coordinate with project managers and finance teams to ensure accurate financial reporting and closeouts.
Scale Army Careers is a staffing company that connects contractors with global clients. This role supports a global integrated creative marketing agency known for high-visibility projects and a fast-paced, collaborative environment.
Build and own client-facing web dashboards with interactive financial models, scenario sliders, and drill-down reporting.
Create AI automations and database queries that connect live accounting data to forecasting and client workflows.
Work directly with clients and teach internal accountants to build tools, owning issues from data discrepancies to shipped solutions.
SPRCHRGR is a professional services consultancy delivering fractional CFO, controllership, and workflow automation to growth-focused US businesses. We are a small, fast-moving team that values collaboration, learning, and efficiency, and we build custom tools instead of off-the-shelf platforms.
Drive financial performance, planning, and analysis to support strategic decision-making in a fast-growing tech environment.
Build financial models and executive dashboards that provide actionable insights across revenue, costs, and cash flow.
Partner with leadership to optimize profitability and enable international expansion in blockchain and digital finance.
Partner company of Jobgether operating at the intersection of technology, digital finance, and blockchain innovation. Fast-growing and globally distributed, with a culture emphasizing financial discipline, ownership, and continuous improvement.