Applied Research Scientific AI

Skills

About the Role

You will build long-horizon scientific-research environments and post-train agents that search literature, use scientific databases and domain tools, run code, and choose experiments. You will design verifiers, develop reinforcement-learning methods, and maintain reproducible code, data, logs, and experiment configurations.

Requirements

• Depth in reinforcement learning, agents, or post-training systems
• Experience building and debugging model-training, post-training, agent, or evaluation loops
• Experimental judgment, including baselines, trace inspection, and failure attribution
• Python
• Ability to build reproducible artifacts for researchers and engineers
• Ability to own ambiguous problems and communicate with partners

Responsibilities

• Build environments for literature search, scientific databases, code, domain tools, and experiment selection
• Turn partner workflows, datasets, and outcome criteria into trainable tasks, evaluations, and reward signals
• Design verifiers for correctness, novelty, reproducibility, and evidence use
• Connect programmatic checks, simulations, domain models, and expert feedback to training
• Develop reinforcement-learning and multi-agent methods for proposing, testing, and critiquing hypotheses
• Maintain reproducible code, data, logs, and experiment configurations

Benefits

• Flexible work
• Visa sponsorship and relocation support
• Team off-sites and conference attendance