Remote Applied AI Researcher — RL & Multi-Agent Systems

Prime Intellect, Inc.; United States; Remote; USD 150.000 - 300.000; Vollzeit

Benefits dieser Stelle

Visa sponsorship

Relocation support

Professional development budget

Conference attendance

Zusammenfassung

Prime Intellect is seeking researchers to build and post-train agents that navigate literature, run code, and use domain tools within defined budgets. You will turn workflows and data into trainable tasks with evaluators and reward signals, while ensuring reproducibility of research code and environments.

The role spans autonomous research and partner-facing work, with flexible, international remote options and strong equity incentives.

Qualifikationen

• Depth in RL, agents, or post-training systems; hands-on experience building and debugging model-training, post-training, agent, or evaluation loops.
• Strong experimental judgment, meaningful baselines, careful trace inspection, clear failure attribution.
• Strong Python; ability to build artifacts that other researchers and engineers can run, inspect, and extend.

Aufgaben

• Build long-horizon environments where agents search literature, query databases, run code and domain tools, and choose experiments within fixed compute or budgets.
• Turn research partners' workflows, datasets, and outcome criteria into trainable tasks, evaluations, and reward signals; design verifiers for correctness, novelty, and reproducibility.
• Develop RL and multi-agent methods, keep code/data/logs reproducible, and release reusable environments and research code.

Kenntnisse

Python

RL

Agents

Post-training

Jobbeschreibung

Prime Intellect is seeking researchers to build and post-train agents that navigate literature, run code, and use domain tools within defined budgets. You will turn workflows and data into trainable tasks with evaluators and reward signals, while ensuring reproducibility of research code and environments.

The role spans autonomous research and partner-facing work, with flexible, international remote options and strong equity incentives.