Remote RL Engineer - Research-Driven AI & Agent Learning

Placements24; Gqeberha; Hybrid; ZAR 1,200,000 - 1,800,000; Full time

Benefits offered by this job

Competitive Salary

Fully Remote

Research & Publication Opportunities

Computing Resources

Conference Allowance

Health Benefits

Home Office Setup

Job summary

Placements24 is seeking a Reinforcement Learning (RL) specialist to join our fully remote team. You will design, implement, and train RL agents across robotics, game AI, and optimization, working closely with researchers from home in Port Elizabeth area or anywhere globally.

A deep theoretical foundation and practical RL experience are essential. Responsibilities include developing advanced RL algorithms, configuring simulation environments, analyzing agent behavior, and contributing to

Qualifications

• Advanced degree in CS/AI with RL focus.
• Proven hands-on experience applying RL to real-world problems.
• Strong programming skills in Python and ML libraries.

Responsibilities

• Design, implement, and train RL agents for diverse applications.
• Develop and apply advanced RL algorithms (Q-learning, Policy Gradients, Actor-Critic, Deep RL).
• Set up and manage simulation environments for training/testing RL agents.
• Analyze agent behavior, debug issues, and optimize performance for deployment.
• Collaborate with domain experts to define RL-suitable problems.
• Conduct research into novel RL techniques and publish findings.

Skills

Reinforcement Learning

Python

TensorFlow

PyTorch

JAX

Git

Education

M.S./Ph.D. in Computer Science or AI (RL focused)

Tools

Stable Baselines

RLlib

OpenAI Gym

MuJoCo

Job description

Placements24 is seeking a Reinforcement Learning (RL) specialist to join our fully remote team. You will design, implement, and train RL agents across robotics, game AI, and optimization, working closely with researchers from home in Port Elizabeth area or anywhere globally.

A deep theoretical foundation and practical RL experience are essential. Responsibilities include developing advanced RL algorithms, configuring simulation environments, analyzing agent behavior, and contributing to