Similar Jobs
See allApplied Research - Forward-Deployed RL
Prime Intellect
Global
Python
Reinforcement Learning
Post-training
Applied Research - Scientific AI
Prime Intellect
Global
Python
Reinforcement Learning
AI Agents
Applied Research - Quantitative Finance
Prime Intellect
Global
Reinforcement Learning
AI Agents
Python
Research Engineer - Data and Evaluation
Prime Intellect
Global
Python
Data Pipelines
Evaluation Systems
Applied AI Research Engineer
Appen
India
Machine Learning
Software Engineering
Reinforcement Learning
Role Impact:
- Build post-training and evaluation systems for multimodal agents.
- Focus on computer-use agents that recover from mistakes.
Responsibilities:
- Turn real workflows into tasks, environments, and rewards.
- Run post-training experiments and deploy what works.
What you will own:
- Multimodal environments from partner workflows.
- Agent training and evaluation pipelines.
Requirements:
- Experience with RL, agents, or post-training.
- Strong Python and experimental judgment.
Prime Intellect
Prime Intellect is building the open superintelligence stack, providing infrastructure for post-training frontier AI models. The company has raised $150M in funding and fosters a culture of ownership and collaboration for ambitious AI teams.