Strategy Consultant - AI Training & Evaluation

About the Role

Mindrift, supported by Toloka, is building domain-focused reinforcement learning environments, task sets, and evaluation systems for advanced AI models. The goal is to convert real practitioner knowledge into structured training material that helps next-generation generative systems learn, reason, and perform more effectively.

This opening is part of a new management consulting domain centered on turning authentic strategy consulting work into realistic learning environments for AI. The team will be made up of consultants from top-tier firms who can translate actual project experience into end-to-end examples, covering problem framing, work planning, analysis, synthesis, and client-ready recommendations.

You will work with a growing group of consulting professionals helping shape how AI develops high-level business reasoning.

Eligibility and Firm Requirement

This position is only open to consultants with direct experience from a recognized top-tier strategy consulting firm. Applicants without hands-on project experience at one of the listed firms should not apply. The eligible firms are McKinsey & Company, Boston Consulting Group (BCG), Bain & Company, Oliver Wyman, Roland Berger, Monitor Deloitte (Deloitte S&C), EY-Parthenon, Kearney, and Strategy& (PwC).

What You Will Do

You will help create realistic consulting scenarios and evaluation materials for AI training. The work involves building project environments based on real engagement dynamics, designing tasks that mirror practical consulting workflows, and defining how those tasks should be assessed.

• Develop realistic consulting project environments with details such as industry setting, financial context, constraints, competing inputs, and missing information.
• Create structured consulting tasks for AI agents, including work such as market sizing, commercial due diligence, cost optimization, growth strategy, operational diagnosis, benchmarking, and similar analyses.
• Set evaluation standards by building grading rubrics, quality frameworks, and gold-standard answers that will be used to calibrate an LLM-based scoring system for AI outputs.

This is a remote, project-based role for an individual contributor who will focus on analytical design and evaluation work.

Candidate Profile

Ideal applicants have at least 3 years of experience at one of the eligible consulting firms and bring direct project experience in problem structuring, analytical work, and client-facing delivery.

• At least 3 years of experience at McKinsey, BCG, Bain, Oliver Wyman, Roland Berger, Monitor Deloitte, EY-Parthenon, Kearney, or Strategy&.
• Strong capability in structured problem-solving and hypothesis-led thinking.
• Ability to turn broad, unclear problems into clear analytical steps and deliverables.
• High standards for logical accuracy and quality of output.
• Comfort with working independently and with minimal supervision.
• Good written English skills at B2 level or higher.

No advanced technical background is needed, and onboarding will be provided for the lightweight tools used in the role.

Compensation

Contributors can earn up to the equivalent of $60 per hour, depending on experience and the pace of contribution. Pay may differ by project based on scope, complexity, and the expertise required.

Additional Information

This is a remote opportunity available on a project basis. The work is focused on analytical design, task creation, and evaluation for AI training purposes.