Research Scientist: Game Agents & Model Distillation

Good Start Labs; Ottawa; Hybrid; CAD 90,000 - 130,000; Full time

Job summary

Good Start Labs is recruiting for a research-focused role in Ottawa that combines game AI with scalable language-model distillation. You will train superhuman game agents, distill insights into general models, and design benchmarks using the game engine as a verifier.

The work emphasizes RL post-training methods (PPO/GRPO/RLVR), designing rewards for multi-agent interactions, and producing publishable results that advance the lab’s research brand.

Qualifications

• Experience building or distilling game agents into general models.
• Public research record with papers, models, or benchmarks.
• Ability to design experiments and derive conclusions from messy results.

Responsibilities

• Train expert game agents and distill their intelligence into general language models.
• Design dense reward signals and shape what gets learned.
• Build training systems that mirror a benchmark and use the game engine as verifier.
• Run supervised fine-tuning and RL experiments measuring game environments impact on model performance.
• Design rewards/evaluations for multi-agent games including negotiation and cooperation.
• Publish papers, technical reports, and blog posts to bolster research brand.

Skills

Reinforcement learning

PPO/GRPO/RLVR

Game AI

Research experience

Publications/ benchmarks

Tools

Python

PyTorch

TensorFlow

Job description

Good Start Labs is recruiting for a research-focused role in Ottawa that combines game AI with scalable language-model distillation. You will train superhuman game agents, distill insights into general models, and design benchmarks using the game engine as a verifier.

The work emphasizes RL post-training methods (PPO/GRPO/RLVR), designing rewards for multi-agent interactions, and producing publishable results that advance the lab’s research brand.