Note: The job is a remote job and is open to candidates in USA. Mindrift, powered by Toloka, is a leading enterprise AI and machine learning data partner focused on connecting top domain experts with cutting-edge AI initiatives. The role involves building domain-specific reinforcement learning environments and structured consulting tasks for AI agents to enhance their learning and evaluation processes.

Responsibilities

• Build realistic consulting project environments — create detailed project scenarios grounded in real engagement dynamics: industry context, financials, constraints, conflicting inputs, and incomplete information
• Design structured consulting tasks for AI agents — break projects into discrete tasks that mirror real consulting work: market sizing, commercial due diligence, cost optimization, growth strategy, operational diagnosis, benchmarking, and more
• Define evaluation criteria and quality standards — develop grading frameworks, evaluation rubrics, and golden-answer solutions for each task, used to train and calibrate an LLM-based grading system that evaluates AI outputs at scale

Skills

• 3+ years at McKinsey, BCG, Bain, Oliver Wyman, Roland Berger, Monitor Deloitte, EY-Parthenon, Kearney, or Strategy&
• Strong structured problem-solving and hypothesis-driven thinking
• Ability to translate vague problems into clear analytical steps and deliverables
• High attention to logical consistency and output quality
• Independent, self-directed working style
• Clear written English (B2+)

Company Overview