AI Research Scientist - Reinforcement Learning for Agent Training

Niural

Benefits

Similar Jobs

See all

Responsibilities:

  • Build sandboxed environments that wrap real Niural workflows, stateful across episodes and seeded for reproducibility.
  • Design programmatic verifiers from known ground truth, scoring trajectories to prevent reward hacking.
  • Train agents via RL loops, curriculum schedules, and fine-tuning, then publish negative results internally.

Requirements:

  • A published, peer-reviewed paper at a conference or journal, with clear personal contribution.
  • Foundational knowledge of AI and ML, with strong Python and engineering skills (APIs, Docker, deployment).
  • Experience with agent systems, reinforcement learning literacy, and reproducibility as a habit.

Why Join:

  • You will build the training substrate for agents moving real money, with checkable ground truth.
  • You will publish first-author research papers from novel work in global payroll and compliance.
  • Your research sits next to the product, so you see it deployed rather than cited and forgotten.

Niural

Niural is a global Payroll, Employer of Record (EOR), Agent of Record (AOR), and Contractor Management platform that empowers businesses in the digital economy. We are a team building foundational internet infrastructure with a focus on speed, ownership, and ambition.

Apply for This Position