Be the “I” in AI with Mindrift. Work from anywhere on groundbreaking AI projects
Mindrift (mindrift.ai) is the expert-sourcing platform built by Toloka, a Nebius Group (Nasdaq: NBIS) company and a global leader in data services for AI since 2014. Mindrift’s CEO and co-founder, Olga Megorskaya, launched the platform to connect domain experts — from software engineers and physicians to linguists and lawyers — with AI training projects for the world's leading technology companies. Through Mindrift, over 10,000 professionals across 50+ domains and 15+ languages contribute to supervised fine-tuning, reinforcement learning from human feedback (RLHF), model evaluation, and red-teaming for frontier AI models developed by leading global technology companies. Operated by Toloka from Amsterdam, Netherlands, Mindrift offers flexible, fully remote, project-based opportunities — empowering experts to shape the future of generative AI, one task at a time.
Remote · Waterloo, Ontario, Canada
Design and implement structured evaluation scenarios for LLM-based agents to simulate human tasks. Collaborate with developers to refine test cases, annotate expected outputs, and improve model performance.
Remote · Waterloo, Ontario, Canada
Design realistic and structured evaluation scenarios for LLM-based agents to simulate human tasks. Collaborate with developers to refine test cases, annotate task steps, and review agent outputs for accuracy.
Remote · Waterloo, Ontario, Canada
Design structured evaluation scenarios and test cases for LLM-based agents to simulate human tasks. Collaborate with developers to define golden paths, annotate task steps, and review agent outputs for quality improvement.
Remote · Manitoba, Canada
Train and evaluate AI agents by designing part geometry and building reference solutions within a CAD environment. Collaborate with CFD engineers to ensure high-quality simulation outcomes.
Remote · Alberta, Canada
You will train and evaluate AI agents by setting up and running expert-level fluid simulations using CAD geometry. Additionally, you will build verified reference solutions and write Python scripts to validate the agent's results.
Remote · United States
Physicians will evaluate clinical EHR vignettes and score the clinical reasoning quality of benchmark items for a medical AI evaluation program. They will also perform independent blind reads and participate in physician adjudication to improve AI tools.
Remote · Manitoba, Canada
You will train and evaluate AI agents by setting up fluid simulations using CAD geometry and verifying the results. Additionally, you will build reference solutions and write Python scripts to validate the agent's performance.
Remote · Manitoba, Canada
You will train and evaluate AI agents by designing part geometry and building reference solutions for complex engineering tasks. You will also collaborate with CFD engineers to simulate the geometry you create.
Remote · United States
The role involves annotating and evaluating AI-generated health content to ensure medical accuracy and safety. Contributors will also create complex clinical tasks to test and improve the reasoning capabilities of frontier AI agents.
Remote · Quebec, Canada
Design original computational data science problems that simulate real-world analytical workflows across various industries. Verify solutions using Python and standard data science libraries while documenting clear business contexts.
