Senior Lead Agentic RL Engineer for Autonomous AI Agents

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

Job summary

UMELIFE (SINGAPORE) PTE. LTD. seeks a Senior Agentic Reinforcement Learning lead to drive next‑gen AI agents capable of autonomously executing long-horizon tasks across virtual environments. You will lead a team, advance LLM post-training and Agent RL, and push boundaries in agent reliability and task completion.

The role involves developing training pipelines with GRPO/PPO, trajectory-based training, and sandbox integration to translate research into real-world capabilities.

Qualifications

• Master's degree or higher with hands-on RL/RLHF/RLVR experience (minimum 3 years).
• Experience leading small teams on end-to-end LLM post-training projects preferred.
• Familiarity with agent-focused projects and long-horizon task goals.

Responsibilities

• Conduct RL training experiments for long-horizon tasks, including hyperparameter tuning and analysis.
• Manage agent trajectory data and sandbox environment integration into the training pipeline.
• Collaborate with evaluation team to improve model success rate on long-horizon tasks.

Skills

Reinforcement Learning

RLHF

RLVR

Agent projects

Education

Master's degree or above

Tools

GRPO

PPO

veRL

OpenRLHF

Job description

UMELIFE (SINGAPORE) PTE. LTD. seeks a Senior Agentic Reinforcement Learning lead to drive next‑gen AI agents capable of autonomously executing long-horizon tasks across virtual environments. You will lead a team, advance LLM post-training and Agent RL, and push boundaries in agent reliability and task completion.

The role involves developing training pipelines with GRPO/PPO, trajectory-based training, and sandbox integration to translate research into real-world capabilities.