AI/ML Engineer

About the role

A long-term hourly contract for someone who already has a working self-play reinforcement-learning system, similar to AlphaZero or MuZero, and can reproduce it on the client's GPU.

What you'll do

• Provide complete working source code for the self-play training pipeline.
• Show training from randomly initialised weights with measurable improvement.
• Provide training logs, checkpoints, and before-and-after evaluation results.
• Reproduce the training on the client's GPU/server and demonstrate the trained agent.

Requirements

• You must ALREADY have a working self-play reinforcement learning project, similar to AlphaZero or MuZero.
• You MUST include a demo video of the training process, the agent playing, and measurable improvement.
• Proposals without a demo video will not be considered.
• Not a fit: new development, pretrained demos, standard PPO/DQN, LLM fine-tuning, or API integrations.

About Upwork client

A client hiring a reinforcement-learning engineer who already has a working self-play training system similar to AlphaZero or MuZero.

AI Alerts shares third-party job opportunities for informational purposes only. We are not the employer and are not involved in the hiring process. Always verify the company and role through official channels before applying, and never pay to apply, train, onboard, process documents, or secure a job offer. Legitimate employers do not ask applicants for money. Read our Terms to learn more.