About GroundTruth

What we do

We test AI systems for labs and enterprises, with ready-to-license benchmarks and custom evaluations for specific models, domains, and use cases.

We also create, enrich, and quality-check training data across multiple modalities, for every stage of your AI training pipeline.

We work with a network of vetted domain experts and generalist annotators to provide the human expertise behind this evaluation and training data. Our platform handles expert vetting, task management, quality control, and payments, allowing us to deliver reliable human judgment at scale.

Who we are

Aman GoutamFounder
Aman works across annotation operations, dataset creation, and AI workflows. He helped grow a global network of 125,000+ annotators in six months for Uber AI Solutions. At GroundTruth, he leads evaluation datasets, model failure analysis, and practical systems that improve AI reliability at scale.
Mohit KhullarCo-founder
Mohit brings operational depth and execution discipline to GroundTruth. He previously built and led annotation teams delivering more than 98% accuracy on global projects for Uber AI Solutions. Today, he focuses on scalable processes, consistent quality, and dependable workflows for AI evaluation and training data.
Miroojin BakshiCo-founder & Research Head · IISc · IIT
Miroojin studies how large language models work and how to evaluate them critically. An IISc and IIT alumnus, he previously worked as a software engineer at Razorpay and Leapfin. As GroundTruth’s co-founder and Research Head, he leads the company’s technical research and evaluation practice.

Connect

If you're a lab or enterprise looking to license a benchmark, commission a custom evaluation, or get help with training data, or if you just want to talk, book a call or email .

Domain experts and generalist annotators looking to get paid for applying human judgment in our projects can sign up on our platform.

Our benchmarks and data are on Hugging Face. Follow us on LinkedIn and X for company updates.