Research Engineer - Environments, Data and Post-Training

About the role

The team works on frontier post-training for AI models. The engineer develops and implements new training and evaluation methods, investigating how data and rewards shape model behavior. This work influences AI models and products through rigorous experimentation and scaled implementation.

Our summary of the posting; the original is on the mercor careers page.

What the posting requires

Required

• Programming
• Machine learning systems
• Post-training
• AI research
• Reinforcement learning
• Open problems
• Language model evaluation
• Data-centric ML
• Machine learning
• Training

Preferred

• Synthetic data generation
• Distributed systems
• APIs
• Backend systems
• Databases
• Experimental design

These tags are our reading of the posting. They can miss something; the original posting is the reference.