reinforcement learning ai scientist.

I am currently working with a company focusing on AI, LLM and Computer Vision.

Salary package attractive! Hybrid working arrangement- 4 days office. Office location near Buona Vista. 4 rounds of interview to offer stage.

about job

• Develop and execute comprehensive RL frameworks to evaluate the safety, performance, and alignment of autonomous agents.
• Build advanced monitoring tools using Bayesian models (GPs, BNNs) to quantify system risk and confidence levels.
• Architect and maintain testing infrastructure to debug and validate non-deterministic software systems.
• Conduct technical "red-teaming" and benchmarking using specialized methods like PPO and RLHF.
• Manage the full technical lifecycle from environmental interfacing to policy optimization.
• Translate complex theoretical designs into high-quality, production-ready code under senior technical mentorship.

skills and requirements

• Strong academic background in a quantitative field such as Mathematics, Physics, or Machine Learning theory.
• Expert-level proficiency in the Python ecosystem, specifically NumPy and PyTorch.Hands-on experience with Reinforcement Learning techniques, including Trust Region methods and RLHF.
• Practical knowledge of Bayesian Machine Learning models like Gaussian Processes or Bayesian Neural Networks.
• Demonstrated ability to design automated testing frameworks and debug complex, non-linear systems.
• Familiarity with Multi-Agent RL (MARL) technologies and a keen interest in applied AI safety research is a significant plus.