RL environments and training data for frontier AI labs. Backed by Y Combinator.
About the role
Share a system, experiment, benchmark, paper, or open-source contribution you are proud of. Explain what you built, what failed, and what you learned. Found on 1752vc Careers, the job board for startup and VC roles.
What they're looking for
- Any (new grads ok) of experience
- US citizen/visa only
- Full-time Engineering role
More about this role
About Klavis AI
Klavis AI builds RL environments and high-quality training data for frontier AI models. We work across long-horizon coding, AI4Science, AI4AI, knowledge work, and agentic tool use.
The role
We are hiring a Research Engineer to turn questions about agent learning into reliable systems and reproducible experiments. Work directly with the founders to build environments, datasets, and evaluations, and study how task design, rewards, and verification affect model capabilities.
What you will work on
• Build realistic multi-step tasks, isolated runtimes, reference solutions, and verifiers, including environments in Harbor format.
• Develop pipelines for high-quality data generation, environment orchestration, agent rollouts, evaluation, and quality control at scale.
• Run controlled experiments on task difficulty, curricula, reward design, and long-horizon agent behavior.
• Analyze failures and reward exploitation, and build evaluations that measure generalization.
• Work with domain experts to turn scientific and knowledge-work workflows into reproducible training environments.
What you bring
• Strong experience with containers, data pipelines, and reliable experiment...
Browse similar: AI jobs · AI startup jobs · Startup jobs · Remote jobs · San Francisco Bay Area