Senior Agent RL Engineer: Lead Autonomous AI Agents

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

Job summary

UMELIFE (SINGAPORE) PTE. LTD. is seeking a Senior Agentic Reinforcement Learning (RL) lead capable of directing development of autonomous AI agents for long-horizon tasks in virtual environments. You will oversee end-to-end RL post-training initiatives, shaping agent behavior and reliability.

You will guide a small team, push the boundaries of agent autonomy, and collaborate with research and evaluation teams to translate cutting-edge RL research into robust, real-world capabilities.

Qualifications

• Master’s degree or higher with at least 3 years’ hands-on RL experience.
• Experience leading a small team on end-to-end LLM post-training projects.
• Experience with RL algorithms like GRPO/PPO and LLM training frameworks veRL/OpenRLHF.

Responsibilities

• Conduct RL training experiments for long-horizon tasks, including hyperparameter tuning and iterative optimization.
• Manage agent trajectory data feedback and integration into the training pipeline, as well as coordinate and optimize sandbox environment integration.
• Work closely with the evaluation team to validate model capabilities, analyze evaluation results, and continuously improve the model's success rate on long-horizon tasks.

Skills

Agentic RL

Leadership

Experimentation

Education

Master's degree or above

Tools

GRPO

PPO

veRL

OpenRLHF

Job description

UMELIFE (SINGAPORE) PTE. LTD. is seeking a Senior Agentic Reinforcement Learning (RL) lead capable of directing development of autonomous AI agents for long-horizon tasks in virtual environments. You will oversee end-to-end RL post-training initiatives, shaping agent behavior and reliability.

You will guide a small team, push the boundaries of agent autonomy, and collaborate with research and evaluation teams to translate cutting-edge RL research into robust, real-world capabilities.