Head Agentic RL Engineer: Autonomy-Driven LLM Post-Training

KUAILU SOFTWARE (SINGAPORE) PTE. LTD.; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

KUAILU SOFTWARE (SINGAPORE) PTE. LTD. seeks a Senior or Head Agentic Reinforcement Learning (RL) leader to drive next-generation AI agents capable of autonomously completing long-horizon tasks in virtual environments.

You will lead a team focused on agent autonomy, reliability, and real-world applicability, advancing RL, RLHF, RLVR, and LLM post-training techniques in sandboxed and evaluated settings.

Qualifications

• Master's degree or higher with 3+ years RL experience.
• Experience with RL algorithms such as GRPO and PPO.
• Experience leading a small team in end-to-end LLM post-training projects.

Responsibilities

• Lead RL experiments for long-horizon tasks and hyperparameter tuning.
• Coordinate sandbox environment integration and trajectory data feedback.
• Collaborate with evaluation team to improve model success rate.

Skills

RL

RLHF

RLVR

Team leadership

LLM training

Education

Master's degree

Tools

veRL

OpenRLHF

GRPO

PPO

Job description

KUAILU SOFTWARE (SINGAPORE) PTE. LTD. seeks a Senior or Head Agentic Reinforcement Learning (RL) leader to drive next-generation AI agents capable of autonomously completing long-horizon tasks in virtual environments.

You will lead a team focused on agent autonomy, reliability, and real-world applicability, advancing RL, RLHF, RLVR, and LLM post-training techniques in sandboxed and evaluated settings.